© 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. 84208
    Prev
    Next
    INDEX
    Explanations

    historical centuries

    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
    廰
    -2.59
    костюм
    -2.55
    ではでは
    -2.50
    をしました
    -2.50
     the
    -2.47
    を行いました
    -2.45
    鵙
    -2.44
    馓
    -2.44
    をもら
    -2.42
    genodigd
    -2.39
    POSITIVE LOGITS
    <em>
    3.09
    (
    2.92
    、
    2.66
    （
    2.63
    you
    2.27
     exuberant
    2.22
     artful
    2.19
    It
    2.19
     '
    2.17
    你在
    2.16
    Activations Density 0.011%

    No Known Activations