© 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. 22-GEMMASCOPE-2-RES-16K
    7. 10452
    Prev
    Next
    INDEX
    Explanations

    yes, absolutely

    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_22_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
    gesetz
    0.90
    념
    0.89
    maks
    0.88
    ван
    0.87
    ्म
    0.86
     azo
    0.85
    ीय
    0.84
    <0xBF>
    0.84
    worthiness
    0.82
     विस्फोटक
    0.82
    POSITIVE LOGITS
    IOR
    1.12
    หลาย
    1.07
    apati
    1.05
     molti
    1.04
    pai
    1.04
     numerosos
    1.03
    Sen
    1.02
     Sen
    0.98
    多数
    0.98
    egal
    0.97
    Activations Density 0.015%

    No Known Activations