© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 239860
    Prev
    Next
    INDEX
    Explanations

    articles and numbers followed by words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    pits
    0.50
     pits
    0.45
    neighbors
    0.45
     Helmut
    0.44
     divisors
    0.42
    tym
    0.42
    帶
    0.42
     sockaddr
    0.42
     collars
    0.42
     lugs
    0.42
    POSITIVE LOGITS
    ֶ
    0.45
    ㅊ
    0.43
     نظری
    0.43
     creciente
    0.43
     уровнем
    0.43
     bütün
    0.42
     Autón
    0.42
    .);
    0.42
    گے
    0.42
     완
    0.42
    Activations Density 0.001%

    No Known Activations