© 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. 39849
    Prev
    Next
    INDEX
    Explanations

    set, get, update, sort operations

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

    The neuron fires on action‐word identifiers in code, i.e. tokens that are imperative verbs (like Get, Set, Start, Stop, detach, attach, install, etc.) in function or method names.

    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
     attente
    -1.35
     malen
    -1.34
     constater
    -1.34
    urface
    -1.34
    
    -1.31
     faciliter
    -1.30
    鹟
    -1.29
    ㍑
    -1.28
     素描
    -1.28
     唯美
    -1.28
    POSITIVE LOGITS
     from
    1.52
     F
    1.41
     eight
    1.38
     first
    1.37
     as
    1.37
     after
    1.36
     before
    1.36
     taking
    1.36
     M
    1.34
    ၀
    1.34
    Activations Density 0.004%

    No Known Activations