© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 7047
    Prev
    Next
    INDEX
    Explanations

    setting false makes

    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
    จาก
    -1.71
    ੨
    -1.65
     personalización
    -1.60
    และ
    -1.56
    </h5>
    -1.51
     gastronomía
    -1.51
     financiación
    -1.49
     และ
    -1.47
    %");
    -1.45
     時計
    -1.45
    POSITIVE LOGITS
     However
    1.45
    на
    1.41
     tū
    1.39
     kū
    1.38
     Although
    1.38
    Although
    1.38
     peringatan
    1.36
    although
    1.34
    Another
    1.33
     that
    1.32
    Activations Density 0.005%

    No Known Activations