Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 11833
    Prev
    Next
    INDEX
    Explanations

    code keywords and structure

    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
    ковый
    -0.99
     sumber
    -0.97
     two
    -0.97
     also
    -0.90
     second
    -0.90
     three
    -0.88
     water
    -0.87
     Si
    -0.86
    ᵘ
    -0.82
    ➙
    -0.82
    POSITIVE LOGITS
    Ѐ
    1.01
     невели
    0.99
    🏓
    0.97
     inext
    0.96
     transparence
    0.94
     confidentialité
    0.93
     Aene
    0.92
    튿
    0.92
    苳
    0.91
     refe
    0.90
    Activations Density 0.030%

    No Known Activations