© 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. 63102
    Prev
    Next
    INDEX
    Explanations

    dates and names

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

    faces accusations

    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
    OfDeath
    0.46
    支
    0.41
     websocket
    0.40
    Fool
    0.38
    asmuch
    0.37
    要知道
    0.37
    はある
    0.36
    พน
    0.36
    plet
    0.36
    癤
    0.36
    POSITIVE LOGITS
     enqu
    0.44
     revital
    0.43
     Caroline
    0.42
    लाईन
    0.42
     riverside
    0.39
     Midwestern
    0.39
     Campaigns
    0.39
     кампа
    0.38
     Singers
    0.38
     Mary
    0.38
    Activations Density 0.000%

    No Known Activations