© 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. 129023
    Prev
    Next
    INDEX
    Explanations

    programming language keywords

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

    The neuron fires on function or method definition lines (e.g. visibility keywords plus return type and name in various languages).

    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
     bluz
    -1.90
     consommateurs
    -1.69
     этом
    -1.68
     salonu
    -1.67
     dekol
    -1.66
    ถ้า
    -1.65
     balkon
    -1.62
     tunik
    -1.59
     abiye
    -1.59
     ekip
    -1.54
    POSITIVE LOGITS
     the
    2.34
     it
    2.30
     does
    1.79
     or
    1.65
     of
    1.65
     at
    1.64
     any
    1.64
     which
    1.62
     is
    1.59
    0
    1.57
    Activations Density 0.010%

    No Known Activations