© 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. 84704
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    筈
    -1.16
    żeli
    -0.97
     {{$
    -0.95
    ченным
    -0.93
    ତ
    -0.92
     standpoint
    -0.91
    ijos
    -0.90
    적으로
    -0.89
     rör
    -0.89
     Ін
    -0.88
    POSITIVE LOGITS
     karya
    0.96
     armas
    0.94
     będ
    0.93
    </em>
    0.91
    wack
    0.90
     certe
    0.89
     bcrypt
    0.88
     unangemessene
    0.88
    kespeare
    0.87
     devint
    0.86
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.