© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 28366
    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
     to
    -1.23
    \
    -1.21
     necessarily
    -1.09
     you
    -1.08
    en
    -1.08
    I
    -1.06
     nhôm
    -1.04
    );
    -1.03
     衣装
    -1.03
     neceff
    -1.02
    POSITIVE LOGITS
     sekä
    1.11
    ampiyon
    1.09
     Они
    1.09
     moderne
    1.09
     répar
    1.05
    ずつ
    1.05
     regarde
    1.05
     señalar
    1.03
     

    1.03
    вое
    1.03
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.