© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 10580
    Prev
    Next
    INDEX
    Explanations

    examine, verify, monitor, debug

    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
    ኬ
    1.03
    組立
    1.03
     帽子
    1.03
    แจ
    0.96
    帽子
    0.95
     イン
    0.95
    0.94
     త
    0.94
     あ
    0.93
    0.92
    POSITIVE LOGITS
    ə
    1.80
    ərə
    1.71
     və
    1.62
     mə
    1.61
    Ə
    1.57
    ət
    1.55
    mə
    1.53
    ər
    1.53
     ə
    1.50
     hə
    1.50
    Activations Density 0.009%

    No Known Activations