© 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. 65782
    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
    примеча
    -1.27
    жены
    -1.23
     sved
    -1.20
     Policía
    -1.16
     AÑOS
    -1.16
    xvi
    -1.16
     évé
    -1.16
     Selección
    -1.15
     veuillez
    -1.14
    lucht
    -1.13
    POSITIVE LOGITS
     and
    1.47
    orithms
    1.15
    みて
    1.05
    Tomasz
    1.02
    1
    1.01
    Adic
    0.98
    Sylvie
    0.97
    8
    0.97
     Поэтому
    0.97
    Mó
    0.96
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.