© 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. 92364
    Prev
    Next
    INDEX
    Explanations

    announcement or retirement

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

    acquiring or avoiding

    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
     getDate
    0.54
     政
    0.53
     [])
    0.52
     createFile
    0.50
    AdType
    0.49
     夏季
    0.49
     organizers
    0.48
     getTime
    0.48
     カラ
    0.47
     Regime
    0.47
    POSITIVE LOGITS
    ”
    0.55
    of
    0.54
    スピ
    0.50
    or
    0.50
    This
    0.50
    at
    0.48
    Height
    0.48
    on
    0.45
    essential
    0.45
    та
    0.45
    Activations Density 0.000%

    No Known Activations