© 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. 148667
    Prev
    Next
    INDEX
    Explanations

    describe below

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

    Afterward

    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
     napkins
    0.50
    la
    0.48
    ↵
    0.48
     alcohols
    0.48
    ली
    0.47
    le
    0.46
     liquids
    0.46
     incorporated
    0.46
    os
    0.45
     pharmaceuticals
    0.45
    POSITIVE LOGITS
     Mitgl
    0.50
    庀
    0.49
    Universität
    0.48
    İlk
    0.48
     Afterward
    0.47
     Afterwards
    0.46
     虽然
    0.46
     결정
    0.45
    虽然
    0.44
    ütfen
    0.44
    Activations Density 0.000%

    No Known Activations