© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 33557
    Prev
    Next
    INDEX
    Explanations

    computer, networking, cells, workpiece, CNC, IRS, unit, phone

    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
     of
    -1.71
    の方に
    -1.52
     and
    -1.52
    あー
    -1.39
    ところに
    -1.38
    の方も
    -1.35
    にします
    -1.33
    に見える
    -1.31
    向けの
    -1.30
    に似
    -1.29
    POSITIVE LOGITS
    捗
    1.32
    を
    1.21
    in
    1.16
    例文
    1.16
    on
    1.15
    である
    1.15
    では
    1.09
    もあって
    1.07
    c
    1.05
    ↵
    1.05
    Activations Density 0.033%

    No Known Activations