© 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. 183341
    Prev
    Next
    INDEX
    Explanations

    this realm

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

    Cluster puts the Strengths consideration Wiki

    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
     diren
    0.53
     objectMapper
    0.45
     daqu
    0.45
    getCell
    0.42
     collectives
    0.42
    anager
    0.42
    adress
    0.41
     $=
    0.40
     directorial
    0.40
    Wi
    0.40
    POSITIVE LOGITS
    審
    0.48
    り
    0.47
    鳇
    0.47
    福島
    0.47
    くと
    0.46
    明る
    0.46
    レビ
    0.46
    ༸
    0.45
    一番
    0.45
    えると
    0.45
    Activations Density 0.001%

    No Known Activations