© 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. 11109
    Prev
    Next
    INDEX
    Explanations

    Full-service texts

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

    The neuron is looking for high-level procedural or list-structure cues—e.g. imperative step verbs and the punctuation that delimits complex instructions.

    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
    alarına
    0.83
     bezeichnet
    0.80
    از
    0.79
    லாமல்
    0.79
    ხვევ
    0.77
    ojen
    0.77
    r
    0.77
    ازت
    0.74
     rpg
    0.74
    azy
    0.74
    POSITIVE LOGITS
     وبعد
    0.73
    s
    0.72
    aircraft
    0.71
    сім
    0.70
    ้
    0.70
     thẩm
    0.69
     وعلى
    0.67
     Mig
    0.66
    populations
    0.66
    Tinh
    0.65
    Activations Density 0.001%

    No Known Activations