© 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. 22-GEMMASCOPE-RES-131K
    7. 13165
    Prev
    Next
    INDEX
    Explanations

    code actions

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

    The neuron fires on code tokens that are method or function names—particularly verbs used for calls in APIs or libraries.

    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
     astounding
    -1.95
     dando
    -1.91
     VERY
    -1.90
     absurd
    -1.90
     gigantic
    -1.88
     !!!!!
    -1.85
     strikingly
    -1.85
     REALLY
    -1.85
     colossal
    -1.84
     tranquil
    -1.84
    POSITIVE LOGITS
     from
    3.23
     with
    2.83
     what
    2.66
     both
    2.42
     through
    2.28
     each
    2.20
     using
    2.20
     without
    2.16
     all
    2.09
     these
    2.06
    Activations Density 0.019%

    No Known Activations