© 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. 22-GEMMASCOPE-RES-131K
    7. 65906
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     have
    -1.95
     during
    -1.91
     which
    -1.89
     heightened
    -1.85
     at
    -1.85
     from
    -1.76
     where
    -1.75
     enables
    -1.72
     get
    -1.70
     Creating
    -1.70
    POSITIVE LOGITS
    </b>
    2.30
    </strong>
    2.17
     opulent
    1.73
     ornate
    1.65
    outSlope
    1.61
     flamboyant
    1.61
     impromptu
    1.60
    </em>
    1.58
     horrid
    1.57
     Dinas
    1.56
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.