© 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. 10-GEMMASCOPE-RES-131K
    7. 14179
    Prev
    Next
    INDEX
    Explanations

    hydrophilic, mathematical terms, code declarations

    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_10/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
    vereign
    -1.84
    dddd
    -1.70
    ?(
    -1.69
     Septembre
    -1.59
    fying
    -1.57
    vereignty
    -1.57
    nthe
    -1.56
    ofern
    -1.55
    llllllll
    -1.54
    了一眼
    -1.53
    POSITIVE LOGITS
     each
    2.25
     it
    1.71
     all
    1.70
     every
    1.64
     these
    1.53
    はずです
    1.53
     some
    1.52
     our
    1.52
     ところ
    1.49
    のご紹介
    1.47
    Activations Density 0.001%

    No Known Activations