© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 64637
    Prev
    Next
    INDEX
    Explanations

    outside or by

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bino
    -0.93
     výstav
    -0.90
     Głów
    -0.87
    setToolTip
    -0.86
     cubrir
    -0.84
     secado
    -0.83
     Ghosh
    -0.83
    uresh
    -0.83
     awalnya
    -0.82
    sightly
    -0.82
    POSITIVE LOGITS
     via
    1.40
     it
    1.13
     with
    1.04
    呜呜
    1.00
    via
    0.98
     poprzez
    0.98
     by
    0.98
     from
    0.96
     avec
    0.96
     decis
    0.91
    Activations Density 0.108%

    No Known Activations