© 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. 34-GEMMASCOPE-RES-131K
    7. 79229
    Prev
    Next
    INDEX
    Explanations

    classes like btn, label, sm, bordered

    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_34/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
     that
    -0.86
     sapi
    -0.84
     نک
    -0.77
    פל
    -0.77
     conferencias
    -0.75
     jedna
    -0.75
    Cordialement
    -0.74
    InnerText
    -0.74
    ſer
    -0.72
    papa
    -0.72
    POSITIVE LOGITS
     Bengal
    0.81
    的花
    0.78
    WHITE
    0.77
     bri
    0.76
     noexcept
    0.76
    чих
    0.75
     Dot
    0.75
     bribes
    0.74
    square
    0.73
    pixmap
    0.72
    Activations Density 0.003%

    No Known Activations