© 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. 63081
    Prev
    Next
    INDEX
    Explanations

    PU FOAM

    np_acts-logits-general · gemini-2.5-flash-lite

    form biofilms with colours

    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
    Not in Any Lists

    No Comments

    Negative Logits
    坚持
    0.50
    抓住
    0.48
    秤
    0.48
    N
    0.47
    ngths
    0.47
    L
    0.46
    经营
    0.46
    𝙇
    0.44
    也就是说
    0.44
    K
    0.44
    POSITIVE LOGITS
     (`
    0.49
     morphism
    0.49
     morphological
    0.47
    นวน
    0.46
     xmas
    0.45
     foram
    0.45
     inland
    0.45
     travelled
    0.44
     undermines
    0.44
     archaeology
    0.44
    Activations Density 0.000%

    No Known Activations