© 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. 15075
    Prev
    Next
    INDEX
    Explanations

    programming type declarations

    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
    ского
    -2.88
    㩒
    -2.72
    人是
    -2.72
    '
    -2.61
    ness
    -2.53
    that
    -2.52
    ."
    -2.50
     \_
    -2.42
     スタンド
    -2.41
    的基本
    -2.39
    POSITIVE LOGITS
    ⢪
    3.05
    ⚋
    2.81
     anderen
    2.63
     avec
    2.56
    嚳
    2.53
     otros
    2.53
    Kaip
    2.50
    𐍆
    2.47
    Detta
    2.47
     einem
    2.42
    Activations Density 0.091%

    No Known Activations