© 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. 38762
    Prev
    Next
    INDEX
    Explanations

    sculpture

    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
    ak
    1.80
    ا
    1.77
    ن
    1.66
    ता
    1.62
    ну
    1.60
    ном
    1.60
    जन
    1.58
    ти
    1.53
    क
    1.51
    та
    1.50
    POSITIVE LOGITS
     Loại
    1.71
     prioritize
    1.57
    kan
    1.55
     prioritized
    1.54
    to
    1.52
     apprehensive
    1.51
     prioritise
    1.50
     reprieve
    1.50
     tolerate
    1.49
     এসময়
    1.48
    Activations Density 0.005%

    No Known Activations