© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 74217
    Prev
    Next
    INDEX
    Explanations

    Access-Control-Allow-Origin

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

    The neuron detects code identifier tokens (variable, function, and module names) in source files.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     of
    -2.20
     They
    -1.82
     about
    -1.82
    They
    -1.68
     This
    -1.66
     этого
    -1.59
    they
    -1.59
     это
    -1.58
     этом
    -1.54
     they
    -1.53
    POSITIVE LOGITS
     chyb
    1.69
     १
    1.68
     verschillende
    1.58
     trzec
    1.53
    [
    1.52
     revistas
    1.47
     весьма
    1.46
     szczeg
    1.45
     nabíd
    1.45
    gelijke
    1.45
    Activations Density 0.037%

    No Known Activations