© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 32686
    Prev
    Next
    INDEX
    Explanations

    potential risks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_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
     adecuado
    0.53
     пре
    0.49
     moż
    0.48
     pouvait
    0.47
     Jetzt
    0.47
     могла
    0.46
    <unused2117>
    0.45
     Connor
    0.45
     могло
    0.45
     кон
    0.45
    POSITIVE LOGITS
    ால்
    0.49
    و
    0.48
    یکه
    0.47
    Gy
    0.47
    بيت
    0.47
    GIS
    0.44
     gy
    0.44
    folds
    0.43
    وا
    0.43
     GIS
    0.42
    Activations Density 0.001%

    No Known Activations