© 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. 34-GEMMASCOPE-RES-131K
    7. 3099
    Prev
    Next
    INDEX
    Explanations

    sax related words and names

    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_34/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
    nagar
    -0.79
    蒽
    -0.77
    ċi
    -0.76
    Assad
    -0.70
     Council
    -0.68
    Jav
    -0.68
     Dey
    -0.67
    stdint
    -0.65
    stoi
    -0.65
    ماس
    -0.65
    POSITIVE LOGITS
    by
    0.81
    SAX
    0.80
     appeal
    0.80
    holt
    0.79
    證
    0.78
    atile
    0.77
     中古
    0.73
    Frust
    0.73
    xy
    0.72
    //*[@
    0.72
    Activations Density 0.027%

    No Known Activations