© 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. 239804
    Prev
    Next
    INDEX
    Explanations

    slot filler, Muslim territories, needed to, last tank, processing event, keywords as, web pages, poster frame, currently where

    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
    Negative Logits
    irical
    0.44
     TYPE
    0.42
    _
    0.42
     -
    0.42
     confir
    0.42
    icyclic
    0.42
     type
    0.42
    hotel
    0.42
    houette
    0.41
    ِی
    0.41
    POSITIVE LOGITS
    的同时
    0.47
    然而
    0.46
    بود
    0.46
     появления
    0.46
    Assassin
    0.46
     BatchNorm
    0.45
    变为
    0.45
     然而
    0.45
    धारणा
    0.45
    纰
    0.45
    Activations Density 0.001%

    No Known Activations