© 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. 63546
    Prev
    Next
    INDEX
    Explanations

    math symbols and latex

    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
    î
    -0.77
    makeatletter
    -0.71
     Redmi
    -0.70
     elles
    -0.68
     Kardashian
    -0.68
     Cisco
    -0.68
    hidrat
    -0.67
    SplashScreen
    -0.66
    мир
    -0.66
    华为
    -0.65
    POSITIVE LOGITS
    omock
    0.83
    送料
    0.78
     getDescription
    0.73
    vidla
    0.71
     trăng
    0.71
     unico
    0.70
    vode
    0.70
     Tre
    0.69
    talk
    0.69
    協
    0.68
    Activations Density 0.038%

    No Known Activations