© 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. 85420
    Prev
    Next
    INDEX
    Explanations

    said names/titles

    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
     Those
    -1.80
     There
    -1.72
     Many
    -1.68
     These
    -1.65
     Once
    -1.59
     Although
    -1.58
     Often
    -1.58
     Some
    -1.58
     During
    -1.58
     Sometimes
    -1.51
    POSITIVE LOGITS
     vixion
    1.71
    隂
    1.71
     conclud
    1.70
     auffi
    1.65
     yake
    1.65
     RECIPE
    1.64
     kien
    1.63
     zoude
    1.59
     madu
    1.57
     frança
    1.56
    Activations Density 0.034%

    No Known Activations