© 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. 249683
    Prev
    Next
    INDEX
    Explanations

    ordinal indicators, units, and items

    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
     entscheid
    0.54
    лід
    0.46
    ोल
    0.45
    лык
    0.45
    ాత్ర
    0.44
    appel
    0.43
    왜
    0.43
     engan
    0.42
     왜
    0.42
     dessas
    0.42
    POSITIVE LOGITS
     половине
    0.55
    不满
    0.50
     Gossip
    0.49
    选用
    0.48
     Bazaar
    0.46
    پور
    0.46
    细菌
    0.45
    Million
    0.45
    愤怒
    0.44
    一个人
    0.44
    Activations Density 0.001%

    No Known Activations