© 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. 34157
    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
     will
    -1.53
     would
    -1.44
     for
    -1.34
     might
    -1.15
     being
    -1.07
     that
    -1.07
     began
    -1.00
     from
    -0.99
     dünya
    -0.98
     should
    -0.98
    POSITIVE LOGITS
    骉
    1.27
    continued
    1.22
    鷽
    1.19
     attente
    1.17
    atized
    1.16
     dals
    1.06
    banez
    1.05
     Berikut
    1.05
     coû
    1.05
     plik
    1.04
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.