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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 4152
    Prev
    Next
    INDEX
    Explanations

    offensive content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ione
    1.41
    aray
    1.41
    il
    1.33
    n
    1.30
    ick
    1.27
     constriction
    1.27
    aos
    1.26
    icular
    1.22
     возможности
    1.21
     (
    1.18
    POSITIVE LOGITS
     Crimes
    1.65
    ל
    1.56
     horribly
    1.54
    😱
    1.46
    🤮
    1.44
    $("
    1.42
    א
    1.35
    ᴅ
    1.34
    😡
    1.33
    👹
    1.31
    Activations Density 0.781%

    No Known Activations