© 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. 209
    Prev
    Next
    INDEX
    Explanations

    CVE ID

    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
    اتها
    0.85
    ७
    0.85
    ९
    0.82
    ८
    0.82
     szüks
    0.81
    icion
    0.78
    २
    0.78
    ६
    0.77
    uth
    0.77
     snapping
    0.77
    POSITIVE LOGITS
    ½
    1.33
    ¼
    1.13
    ¾
    1.11
     ½
    1.04
    ·
    0.92
    ٫
    0.91
    ⅔
    0.90
    ⅞
    0.86
    ⅝
    0.81
    ″
    0.79
    Activations Density 1.871%

    No Known Activations