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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 198179
    Prev
    Next
    INDEX
    Explanations

    descriptions or questions

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

    located inside/near

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
     as
    0.54
    2
    0.53
    1
    0.52
     ak
    0.47
     praia
    0.46
     ac
    0.46
    ston
    0.45
     प्रत्येक
    0.45
     integrates
    0.45
     each
    0.44
    POSITIVE LOGITS
    过滤
    0.54
     بشأن
    0.50
    不支持
    0.48
    谈
    0.47
    就没有
    0.47
    できなかった
    0.46
     बातचीत
    0.45
     নেতৃত্বের
    0.45
    对话
    0.45
    不想
    0.44
    Activations Density 0.000%

    No Known Activations