© 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. 13-GEMMASCOPE-2-RES-16K
    7. 13095
    Prev
    Next
    INDEX
    Explanations

    NSGs, CJEU, Shell Shape

    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_13_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
    quoi
    2.20
     რომელიც
    1.88
    zeniu
    1.88
     особливо
    1.86
    точ
    1.82
    updateConfirm
    1.78
    ὺ
    1.76
     व्यू
    1.75
    ौज
    1.75
    𝘺
    1.73
    POSITIVE LOGITS
    s
    2.50
    रों
    1.91
    kommt
    1.80
    vn
    1.77
    י
    1.75
    POR
    1.73
    ل
    1.71
    dte
    1.69
    ജീ
    1.68
    सों
    1.63
    Activations Density 0.044%

    No Known Activations