© 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. 92948
    Prev
    Next
    INDEX
    Explanations

    ,v token sequences

    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
    HTTPResponse
    -0.75
    巣
    -0.73
    ᵥ
    -0.72
    DataSetChanged
    -0.71
    SENSOR
    -0.71
    Neptune
    -0.70
     السلام
    -0.70
    OME
    -0.69
    getDay
    -0.69
    TEX
    -0.68
    POSITIVE LOGITS
     ilości
    0.66
     nướng
    0.66
     defining
    0.63
     topography
    0.63
    فظ
    0.62
    setEnd
    0.61
    zelle
    0.61
     Statistica
    0.60
    Torque
    0.60
    定義
    0.60
    Activations Density 0.061%

    No Known Activations