© 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. 11447
    Prev
    Next
    INDEX
    Explanations

    interface Enumerator, streams, similar

    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
     marki
    -0.91
    ケア
    -0.87
    skap
    -0.82
    Referencie
    -0.82
     Où
    -0.82
     dormitorios
    -0.81
     unicornio
    -0.80
     Conseils
    -0.80
    Další
    -0.80
     proveedores
    -0.78
    POSITIVE LOGITS
     Bloc
    0.81
     parentId
    0.79
     Fag
    0.78
    orption
    0.77
     its
    0.76
    żym
    0.76
     требует
    0.75
     setUsername
    0.75
     transmitted
    0.75
     ditto
    0.74
    Activations Density 0.018%

    No Known Activations