© 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. 11422
    Prev
    Next
    INDEX
    Explanations

    legal citations and numbers

    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
    卫生
    -0.91
     „
    -0.84
    „
    -0.82
    Bloc
    -0.81
    пите
    -0.80
    amodel
    -0.79
    Aftermath
    -0.78
     tkinter
    -0.75
    蝓
    -0.74
    ulando
    -0.73
    POSITIVE LOGITS
     dvoj
    0.84
     avenger
    0.79
     čet
    0.78
     Avenger
    0.77
     connects
    0.74
     connections
    0.73
     connection
    0.72
    connection
    0.72
    cauciones
    0.71
    It
    0.70
    Activations Density 0.003%

    No Known Activations