© 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. 186836
    Prev
    Next
    INDEX
    Explanations

    question marks and criticism

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

    following coding conventions

    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
     വര്‍ഷ
    0.53
     棚
    0.49
     পর্যন্ত
    0.49
     CNRS
    0.48
     すぎ
    0.48
    జేపీ
    0.47
     に対
    0.46
     સંદેશ
    0.46
     товар
    0.46
    \}$.
    0.46
    POSITIVE LOGITS
    For
    0.54
    Due
    0.50
    Easy
    0.49
    Group
    0.48
    Over
    0.48
    On
    0.48
    Desde
    0.47
    क
    0.47
    Watch
    0.47
    Prepare
    0.46
    Activations Density 0.001%

    No Known Activations