© 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. 112607
    Prev
    Next
    INDEX
    Explanations

    code and foreign words

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

    underscores in programming code, especially in variable names and identifiers.

    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
     which
    -2.91
     by
    -2.77
     took
    -2.75
     (
    -2.63
     in
    -2.58
     for
    -2.55
     at
    -2.44
     was
    -2.41
     started
    -2.34
     seems
    -2.34
    POSITIVE LOGITS
     utiliser
    2.92
    鷭
    2.48
     envoyer
    2.39
     retourner
    2.36
     arrêter
    2.33
     emporter
    2.30
     créer
    2.25
     groet
    2.20
     acheter
    2.17
     quotidienne
    2.17
    Activations Density 0.018%

    No Known Activations