© 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. 78020
    Prev
    Next
    INDEX
    Explanations

    .org domains

    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
    ulence
    -0.73
    linger
    -0.73
    XP
    -0.71
    ijn
    -0.70
    ODES
    -0.70
     kho
    -0.69
     accompagn
    -0.69
    Zh
    -0.69
     sentido
    -0.68
     cihaz
    -0.68
    POSITIVE LOGITS
    OrderService
    0.69
    Climate
    0.69
     Keim
    0.68
    மா
    0.66
    LOCALE
    0.65
    environment
    0.65
    غراف
    0.64
    Config
    0.64
    jaus
    0.63
     مشار
    0.62
    Activations Density 0.053%

    No Known Activations