© 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. 13119
    Prev
    Next
    INDEX
    Explanations

    code list filtering

    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
     Brodie
    1.82
    ៤
    1.69
     स्यूशन
    1.63
    संख्य
    1.59
    ៥
    1.57
    ४
    1.56
     économique
    1.55
     økonom
    1.53
    ५
    1.53
    樀
    1.53
    POSITIVE LOGITS
    ↵
    1.50
    ↵↵
    1.30
    ,
    1.23
    .
    1.22
     for
    1.17
    or
    1.16
    !
    1.11
     X
    1.10
    ?
    1.10
     »
    1.10
    Activations Density 0.000%

    No Known Activations