© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 130822
    Prev
    Next
    INDEX
    Explanations

    programming language keywords

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

    This neuron fires on tokens that introduce code or style definitions—e.g. CSS selectors (leading “.”), class/func declarations, or other declaration keywords.

    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
    ſu
    -2.02
    ⠀⠀⠀⠀⠀⠀⠀⠀
    -1.91
     véhicules
    -1.91
     fauteuil
    -1.90
    ⠀⠀⠀⠀
    -1.82
     Atención
    -1.80
     capot
    -1.80
     sortant
    -1.79
     commencent
    -1.78
     couvercle
    -1.78
    POSITIVE LOGITS
     in
    2.73
     to
    2.50
    k
    2.45
    b
    2.34
    z
    2.23
    n
    2.19
    g
    2.08
     with
    2.03
     by
    2.03
    c
    2.02
    Activations Density 0.005%

    No Known Activations