© 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. 72743
    Prev
    Next
    INDEX
    Explanations

    code for UI components and data handling

    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
    Salu
    -0.95
    caches
    -0.93
     kdo
    -0.93
     پژوه
    -0.91
    酗
    -0.90
    kelijke
    -0.88
    lás
    -0.87
    gaja
    -0.85
    Suara
    -0.85
    eksi
    -0.85
    POSITIVE LOGITS
     отобра
    1.01
     navíc
    0.88
    まさに
    0.85
     подойдет
    0.83
    listView
    0.80
    álni
    0.80
     дітей
    0.79
    そこに
    0.77
    無料で
    0.77
    さんに
    0.76
    Activations Density 0.017%

    No Known Activations