© 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. 102829
    Prev
    Next
    INDEX
    Explanations

    instructions for certification or bids

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

    alternatives and avoiding drawbacks

    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
    <unused522>
    0.54
    㛣
    0.54
     Omphalodes
    0.50
    ⤟
    0.50
    <unused401>
    0.49
    <unused680>
    0.49
    ContextMenu
    0.47
    <unused2037>
    0.47
    ◐
    0.47
    <unused726>
    0.46
    POSITIVE LOGITS
     votes
    0.43
     certificates
    0.41
     are
    0.41
    ﻫ
    0.41
     sourced
    0.41
     certification
    0.40
     Certificates
    0.39
     defined
    0.39
     blog
    0.39
     dra
    0.38
    Activations Density 0.001%

    No Known Activations