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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 11340
    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
     recently
    -1.08
     which
    -1.08
     Glaub
    -0.93
     veneta
    -0.92
     satuan
    -0.91
     version
    -0.90
     years
    -0.87
     These
    -0.86
     where
    -0.85
     United
    -0.84
    POSITIVE LOGITS
     garantie
    1.12
    媪
    1.03
    埼玉県
    1.02
    ntö
    1.02
    徳島
    1.02
    ;"
    1.01
    ADVERT
    1.01
    ALTH
    0.98
    ktes
    0.96
    腌
    0.96
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.