© 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. 10451
    Prev
    Next
    INDEX
    Explanations

    it's/can

    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
    <strong>
    1.11
    <b>
    0.94
    Corresponding
    0.92
    किसी
    0.91
    отно
    0.89
    ტურ
    0.86
    क्षात
    0.85
    converting
    0.85
     ✅
    0.83
    겉
    0.83
    POSITIVE LOGITS
     Methods
    0.95
     methods
    0.90
     monograph
    0.88
    部长
    0.86
     Equality
    0.85
     Tools
    0.85
     then
    0.83
    颂
    0.82
     servants
    0.82
     Method
    0.81
    Activations Density 0.037%

    No Known Activations