© 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. 14778
    Prev
    Next
    INDEX
    Explanations

    asking questions or wondering

    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
    ;
    -1.45
     from
    -1.45
     -
    -1.40
     in
    -1.38
     a
    -1.32
     due
    -1.24
     being
    -1.23
     based
    -1.22
     with
    -1.20
     Hinblick
    -1.16
    POSITIVE LOGITS
     wondering
    1.83
    Wondering
    1.62
     wondered
    1.57
    みんな
    1.52
    kwür
    1.50
     wonder
    1.50
    Якщо
    1.47
     question
    1.38
    他们的
    1.38
    初めて
    1.38
    Activations Density 0.067%

    No Known Activations