© 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
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 16091
    Prev
    Next
    INDEX
    Explanations

    pinescript

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

    This neuron strongly activates on salient content words—especially longer or less common nouns, verbs, and adjectives—while ignoring common function words.

    oai_token-act-pair · o4-miniTriggered 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
    et
    0.99
    哋
    0.85
    с
    0.75
     abroad
    0.73
     outings
    0.72
    л
    0.72
    р
    0.71
    『
    0.71
    рав
    0.71
    囡
    0.69
    POSITIVE LOGITS
     oczy
    0.86
     independência
    0.85
     بخوان
    0.84
    rukt
    0.80
     kandungan
    0.79
     essai
    0.77
     janeiro
    0.77
     uomini
    0.75
    ylle
    0.75
     സത്യ
    0.75
    Activations Density 0.000%

    No Known Activations