© 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. 14688
    Prev
    Next
    INDEX
    Explanations

    Zynga, Eigen, Strauss, Duane

    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
    “
    -2.70
    ;
    -2.56
     Krzyż
    -2.22
    ا
    -2.14
    :
    -2.14
     perché
    -2.08
    ड
    -2.06
    『
    -2.02
    </h3>
    -2.02
    of
    -2.00
    POSITIVE LOGITS
    และ
    2.86
    に
    2.73
    焌
    2.58
    alakip
    2.48
    熈
    2.39
     experi
    2.39
    见的
    2.33
    鸰
    2.31
     dúvidas
    2.30
    
    2.30
    Activations Density 0.019%

    No Known Activations