© 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. 84838
    Prev
    Next
    INDEX
    Explanations

    concepts and actions

    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
     '-';
    -1.48
     OGSÅ
    -1.47
    muñ
    -1.44
    iyaki
    -1.43
    ?
    -1.41
    Ĝ
    -1.40
    boutin
    -1.40
     <<-
    -1.37
     our
    -1.35
    〕
    -1.32
    POSITIVE LOGITS
     certaines
    1.55
     everything
    1.52
     to
    1.45
     Répondre
    1.36
     something
    1.32
    硨
    1.30
    噐
    1.28
     anything
    1.23
    ]){
    1.18
     sesuatu
    1.17
    Activations Density 0.051%

    No Known Activations