© 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. 226689
    Prev
    Next
    INDEX
    Explanations

    calls, shirt, user, time

    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
    adığı
    0.53
     ભારે
    0.52
    adays
    0.50
     задачу
    0.48
     ച
    0.48
     Zentrum
    0.48
     व्याख्या
    0.47
     വില
    0.46
    ként
    0.46
    ausal
    0.46
    POSITIVE LOGITS
     relating
    0.45
    $,
    0.44
     freg
    0.43
    </b>
    0.43
    >/</
    0.42
     furn
    0.42
     permittee
    0.42
     ning
    0.42
    닌
    0.42
    -\
    0.40
    Activations Density 0.001%

    No Known Activations