© 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. 176996
    Prev
    Next
    INDEX
    Explanations

    updated the

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

    process, grown, and RNA

    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
    srand
    0.57
    Câu
    0.50
    ////
    0.49
     وقلنا
    0.46
    rnd
    0.45
    padding
    0.45
    Nature
    0.45
    //}
    0.45
    rpart
    0.45
    入り
    0.44
    POSITIVE LOGITS
     Hybrid
    0.47
    iyas
    0.47
     Mares
    0.45
     Diam
    0.45
     Saal
    0.44
     hybridization
    0.43
    лено
    0.43
     Orbit
    0.43
    ाइए
    0.43
    ление
    0.42
    Activations Density 0.000%

    No Known Activations