© 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-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 414
    Prev
    Next
    INDEX
    Explanations

    character actions and feelings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     مناطق
    0.99
     TInner
    0.96
    ــ
    0.94
     ProductCategory
    0.93
    Different
    0.92
     _{(
    0.89
     Constraint
    0.89
    Areas
    0.88
     المسا
    0.88
    ـ
    0.88
    POSITIVE LOGITS
    ’
    1.35
     hurriedly
    1.19
    '
    1.16
    ʼ
    1.01
     knew
    0.98
     reluctantly
    0.97
     hesitated
    0.97
     instinctively
    0.96
     asked
    0.95
    itchie
    0.95
    Activations Density 0.769%

    No Known Activations