© 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. 67535
    Prev
    Next
    INDEX
    Explanations

    The translocation, Guerilla, Q:

    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
    u
    -2.11
    M
    -1.79
    %，
    -1.75
    -1.70
     for
    -1.70
    岖
    -1.66
    ちなみに
    -1.66
    線が
    -1.62
    了一
    -1.57
    線の
    -1.55
    POSITIVE LOGITS
    蒞
    2.23
    ícias
    1.87
    Ꮴ
    1.80
    !
    1.80
    踴
    1.78
    䊊
    1.76
     --
    1.73
    咘
    1.73
    蔟
    1.72
    🕗
    1.70
    Activations Density 0.002%

    No Known Activations