© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 109006
    Prev
    Next
    INDEX
    Explanations

    __dirname, __future__, __esModule

    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
    uelta
    -0.81
    Ингредиенты
    -0.80
    ljen
    -0.78
     сіль
    -0.77
    uß
    -0.76
    kez
    -0.75
     implan
    -0.74
    ISSIPPI
    -0.72
     augmented
    -0.72
    Engineering
    -0.72
    POSITIVE LOGITS
     desecha
    0.90
    dirname
    0.89
    ꞉
    0.84
    ferrari
    0.83
    trc
    0.82
     darse
    0.81
     angeb
    0.79
    phir
    0.78
     chai
    0.77
     asociada
    0.77
    Activations Density 0.003%

    No Known Activations