© 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. 11449
    Prev
    Next
    INDEX
    Explanations

    declaring variables or asking questions

    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
     吋
    -1.02
    もちゃ
    -1.01
    IVING
    -1.01
    uluş
    -1.00
     early
    -0.99
    TokenNameDOT
    -0.97
    ⢫
    -0.96
     to
    -0.96
     ört
    -0.93
     tocar
    -0.93
    POSITIVE LOGITS
     برای
    1.10
     для
    1.09
     gustado
    1.07
     такая
    1.03
     Pray
    1.02
     majeurs
    1.01
    我们会
    0.96
     prière
    0.96
     Therefore
    0.95
     we
    0.95
    Activations Density 0.003%

    No Known Activations