© 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. 34-GEMMASCOPE-RES-131K
    7. 48856
    Prev
    Next
    INDEX
    Explanations

    function keywords

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

    The neuron fires on programming‐language tokens and syntax (e.g. keywords like “function” or “false,” braces, punctuation, constants) rather than natural‐language words.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    inctive
    -0.85
    اتی
    -0.79
     Pelosi
    -0.77
     reglas
    -0.74
    small
    -0.73
    RequestMapping
    -0.73
    eky
    -0.71
    デザート
    -0.71
    ngoing
    -0.70
    juelas
    -0.70
    POSITIVE LOGITS
     false
    0.70
     λ
    0.67
     hyal
    0.66
     dukungan
    0.64
     forthwith
    0.63
     художник
    0.63
    Chem
    0.62
    ņu
    0.62
     prioritize
    0.61
     burst
    0.60
    Activations Density 0.035%

    No Known Activations