© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 12287
    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
    llllll
    -1.00
    XIC
    -0.95
     Coupé
    -0.93
     yanında
    -0.93
    了一会儿
    -0.93
    
    -0.91
     membag
    -0.90
     its
    -0.90
    leine
    -0.88
     hedef
    -0.87
    POSITIVE LOGITS
     contextLoads
    1.04
    CÓ
    0.92
     enfermera
    0.90
     copertura
    0.89
     quedará
    0.86
    얻
    0.85
    anolamine
    0.85
     adapta
    0.84
     schließlich
    0.83
    ㄓ
    0.83
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.