© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 14935
    Prev
    Next
    INDEX
    Explanations

    comprehensive fields and subjects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     votre
    -3.08
    </i>
    -3.06
    大叔
    -2.75
    很少
    -2.69
     如果
    -2.69
     Heilige
    -2.59
    小花
    -2.59
     当
    -2.59
     Перейти
    -2.58
    你有
    -2.56
    POSITIVE LOGITS
    屜
    3.16
    一点点
    3.09
    ஂ
    3.03
    ).
    2.98
    )”
    2.88
    稣
    2.86
    6
    2.80
    酲
    2.78
    f
    2.77
    ﾙ
    2.70
    Activations Density 0.008%

    No Known Activations