© 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. 100543
    Prev
    Next
    INDEX
    Explanations

    French, Japanese, Mexican programming terms

    np_acts-logits-general · gemini-2.5-flash-lite

    closing braces or brackets that end code blocks in programming languages.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
     always
    -1.63
     there
    -1.55
     not
    -1.55
    us
    -1.47
     (
    -1.45
     to
    -1.42
     your
    -1.40
     merkwür
    -1.38
     as
    -1.38
    ari
    -1.36
    POSITIVE LOGITS
     Inggris
    1.54
     Jepang
    1.52
    ="">
    1.50
    pentru
    1.49
     Meksiko
    1.48
     jepang
    1.46
     Prancis
    1.45
    atouille
    1.45
    Jeudi
    1.45
     Meksi
    1.45
    Activations Density 0.010%

    No Known Activations