© 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. 78494
    Prev
    Next
    INDEX
    Explanations

    car tires

    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
     chase
    -0.84
     nóng
    -0.82
     بنات
    -0.78
     متری
    -0.69
     mares
    -0.69
    gh
    -0.68
     Gavin
    -0.68
     Bros
    -0.68
    chase
    -0.68
    tamo
    -0.68
    POSITIVE LOGITS
     bald
    0.99
     slick
    0.85
    slick
    0.83
     bias
    0.83
     Slick
    0.77
    効
    0.76
     thoại
    0.75
    Bald
    0.74
     PAH
    0.74
    Slick
    0.72
    Activations Density 0.031%

    No Known Activations