© 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. 128711
    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
    <
    -1.07
     It
    -1.04
     he
    -1.00
    irmer
    -0.94
     Pest
    -0.94
     книги
    -0.93
     falsely
    -0.92
     flagged
    -0.91
    榭
    -0.90
    It
    -0.89
    POSITIVE LOGITS
    鬟
    1.09
    है
    1.03
     рассказыва
    1.03
    ttn
    1.02
     또
    1.01
     firft
    1.01
     Kinda
    1.00
     prenn
    1.00
     různ
    0.98
    kungan
    0.97
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.