© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 3930
    Prev
    Next
    INDEX
    Explanations

    imagine, earth, 你, 这台, 五言

    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
    Negative Logits
    ｫ
    2.95
    <unused1851>
    2.70
    <unused1729>
    2.68
    ្សែ
    2.67
    <unused1625>
    2.61
     ゙
    2.56
     UINavigation
    2.55
    پيديا
    2.54
     BSData
    2.52
    <unused1637>
    2.52
    POSITIVE LOGITS
    ‐
    1.97
    ity
    1.90
    mi
    1.83
    st
    1.77
    ly
    1.75
    mit
    1.70
    wood
    1.64
    hem
    1.61
    man
    1.58
    kin
    1.54
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.