© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 8292
    Prev
    Next
    INDEX
    Explanations

    existence and movement

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron responds to words conveying motion or physical presence (e.g. verbs and nouns around moving, flying, going, being visible, or existing).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    words related to physical presence, existence, or things being visible or tangible in space.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    language describing physical motion and spatial dynamics—things moving, traveling, drifting or floating through space, often highlighting direction, freedom of movement, lightness, or visibility

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     যেটা
    0.77
     payoffs
    0.75
     takeaways
    0.73
     EVERYTHING
    0.71
     जिनको
    0.67
     而且
    0.66
     거고
    0.65
     해서
    0.64
     하다
    0.64
     للغاية
    0.64
    POSITIVE LOGITS
     protop
    0.77
    เคลื่อน
    0.77
    paras
    0.75
    companions
    0.75
     decap
    0.75
    eosin
    0.72
     subsp
    0.72
     majest
    0.71
     pojav
    0.70
    slime
    0.70
    Activations Density 0.087%

    No Known Activations