© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 39144
    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
     I
    -1.20
    $}
    -1.16
     assist
    -1.03
    —
    -1.03
     an
    -1.03
    教堂
    -1.02
     '
    -1.02
     guidance
    -1.00
    合格
    -0.98
     or
    -0.97
    POSITIVE LOGITS
    ってきて
    1.10
     différents
    1.08
     magasiner
    1.05
    
    1.05
    canza
    1.04
    awarkan
    1.04
    gebraucht
    1.03
    娯
    1.03
     lesquelles
    1.02
     naturellement
    1.02
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.