© 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. 67997
    Prev
    Next
    INDEX
    Explanations

    programming contexts

    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
     of
    -2.48
     my
    -1.63
     [
    -1.63
    3
    -1.59
    y
    -1.53
     is
    -1.53
     to
    -1.46
     Be
    -1.45
     You
    -1.45
     et
    -1.45
    POSITIVE LOGITS
     that
    1.91
    グルト
    1.64
     歐
    1.60
     チラシ
    1.57
    ᕱ
    1.55
    🦊
    1.54
     gouden
    1.54
    ㈯
    1.53
     Juventud
    1.52
    👆
    1.52
    Activations Density 0.001%

    No Known Activations