© 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. 12178
    Prev
    Next
    INDEX
    Explanations

    code formatting, punctuation, and special characters

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     by
    -1.09
     after
    -1.05
    providedIn
    -0.95
     fournis
    -0.93
    Preparación
    -0.90
    桎
    -0.88
    after
    -0.88
    َم
    -0.87
    镑
    -0.86
     тыс
    -0.86
    POSITIVE LOGITS
    jména
    1.07
     alumínio
    1.06
     pohled
    1.05
    
    1.05
     trasero
    0.98
    ülen
    0.97
     chrétiens
    0.93
     empaque
    0.92
     oxígeno
    0.91
     TWA
    0.91
    Activations Density 0.003%

    No Known Activations