© 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. 10-GEMMASCOPE-RES-131K
    7. 14542
    Prev
    Next
    INDEX
    Explanations

    year-long periods

    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_10/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
    pecabe
    -1.56
     但是
    -1.56
     prendre
    -1.55
    鉿
    -1.52
     times
    -1.49
     quelques
    -1.48
     kunnen
    -1.47
    сама
    -1.47
    $,
    -1.44
    盉
    -1.44
    POSITIVE LOGITS
    こんばん
    1.39
     which
    1.35
    accéder
    1.34
    ⁉
    1.32
     tengas
    1.30
    ⤴
    1.27
    cionados
    1.27
    becue
    1.25
    Дорогие
    1.25
     that
    1.23
    Activations Density 0.082%

    No Known Activations