© 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. 95816
    Prev
    Next
    INDEX
    Explanations

    code comments

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

    This neuron fires on standalone code identifiers (e.g. variable, class, or function names) in source 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
     唯美
    -1.33
     faſt
    -1.27
     墊
    -1.19
     horloge
    -1.18
     then
    -1.18
     pittores
    -1.17
     菇
    -1.17
     油画
    -1.16
     København
    -1.14
     asisten
    -1.13
    POSITIVE LOGITS
     O
    1.16
     Y
    1.13
     T
    1.11
     H
    1.08
     This
    1.07
     No
    1.05
     P
    1.05
     h
    1.04
     Z
    1.04
     "
    1.00
    Activations Density 0.006%

    No Known Activations