© 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. 96
    Prev
    Next
    INDEX
    Explanations

    parentheses and quotes

    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
     פ
    0.67
     א
    0.65
    ל
    0.65
    Не
    0.64
     По
    0.62
    bound
    0.61
     ไม่
    0.61
    ਸੀ
    0.61
    ಕ್ತ
    0.61
     ק
    0.61
    POSITIVE LOGITS
    gggg
    0.82
    ggg
    0.74
    ly
    0.71
    다고
    0.65
    다면
    0.61
    다는
    0.60
    തിനുള്ള
    0.57
    തിന്
    0.56
    diği
    0.55
    ायतों
    0.55
    Activations Density 3.478%

    No Known Activations