© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 49092
    Prev
    Next
    INDEX
    Explanations

    index after list

    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
    oltre
    -0.79
    UnitTesting
    -0.75
     WASH
    -0.71
     Fillmore
    -0.69
     Parnell
    -0.69
    Swipe
    -0.68
    Прода
    -0.68
    Philli
    -0.68
    pip
    -0.67
    swiper
    -0.67
    POSITIVE LOGITS
    面
    0.71
    Lake
    0.69
     LAKE
    0.67
    りと
    0.65
     Bien
    0.65
     tenements
    0.64
     cadmium
    0.62
     morrer
    0.61
    fahr
    0.60
    getUserInfo
    0.60
    Activations Density 0.048%

    No Known Activations