© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 36375
    Prev
    Next
    INDEX
    Explanations

    code blocks and mathematical expressions

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

    This neuron responds to opening‐parenthesis tokens “(” in code.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     délais
    -2.58
     célè
    -2.52
     éte
    -2.45
    삵
    -2.42
     épar
    -2.39
     voitures
    -2.34
     réve
    -2.34
     clô
    -2.33
     mété
    -2.31
     corrom
    -2.31
    POSITIVE LOGITS
     in
    3.59
     to
    3.00
     as
    2.56
     at
    2.38
     by
    2.31
     or
    2.30
     and
    2.28
     not
    2.28
     with
    2.23
     without
    2.11
    Activations Density 0.013%

    No Known Activations