© 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. 213479
    Prev
    Next
    INDEX
    Explanations

    checkout process, shore excursions, clerical positions, Easter basket creation, o-ring

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

    just before 'predicting' or 'providing'

    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
    q
    0.59
    x
    0.55
    jt
    0.55
    aved
    0.53
    oise
    0.49
    kw
    0.47
    seh
    0.46
    is
    0.46
    w
    0.46
     صاحب
    0.46
    POSITIVE LOGITS
     dikdört
    0.47
     causando
    0.47
     déterminer
    0.47
     bölüm
    0.45
     DUE
    0.45
    ÇA
    0.45
     Paglinawan
    0.44
     rectangle
    0.44
     préparer
    0.44
    ！？
    0.43
    Activations Density 0.000%

    No Known Activations