© 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. 1320
    Prev
    Next
    INDEX
    Explanations

    DPC, GIL, Foundation, Ald, chief

    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
    ❔
    0.86
    觕
    0.79
     zis
    0.77
     Chiu
    0.71
    粓
    0.70
     Claud
    0.70
     spus
    0.69
    羵
    0.69
    olics
    0.69
    轂
    0.68
    POSITIVE LOGITS
    т
    1.06
    ל
    1.06
    و
    0.97
    ו
    0.97
    ור
    0.85
    न
    0.82
    ي
    0.75
    л
    0.73
    ри
    0.73
    н
    0.73
    Activations Density 0.391%

    No Known Activations