© 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. 225298
    Prev
    Next
    INDEX
    Explanations

    law, days, quality, case, Due

    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
     অভিভাবকদের
    0.47
     pleasantly
    0.46
     contoured
    0.45
    рида
    0.44
    њ
    0.44
    тического
    0.43
    шив
    0.43
    <unused67>
    0.42
    ალაქ
    0.42
     laboratoire
    0.42
    POSITIVE LOGITS
    lEdit
    0.53
     Sympt
    0.52
    edTest
    0.51
    langan
    0.50
    l
    0.49
     zwr
    0.48
     Similarity
    0.47
     Decre
    0.47
     implications
    0.46
     Stress
    0.46
    Activations Density 0.000%

    No Known Activations