© 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. 50754
    Prev
    Next
    INDEX
    Explanations

    revoke someone's access

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

    preserve it

    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
    Converted
    0.42
     moim
    0.41
    UserId
    0.40
    Nums
    0.40
    Conversion
    0.39
    Dummy
    0.39
    Denominator
    0.39
    렁
    0.39
     (_,
    0.38
     몇
    0.38
    POSITIVE LOGITS
    ini
    0.41
     Corb
    0.40
    する
    0.39
     শিল্পী
    0.39
    ogel
    0.39
    的故事
    0.38
    lemente
    0.37
     подели
    0.36
    型的
    0.36
    ：“
    0.36
    Activations Density 0.000%

    No Known Activations