© 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. 54025
    Prev
    Next
    INDEX
    Explanations

    keywords from programming languages

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

    The neuron fires on programming‐language identifiers—names of functions, types, libraries, APIs, etc.—in code snippets.

    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
     lã
    -1.23
    鵙
    -1.20
     MÁS
    -1.20
     tênis
    -1.09
     semelh
    -1.08
     hébergement
    -1.07
    に行った
    -1.05
    
    -1.05
    
    -1.05
     และ
    -1.04
    POSITIVE LOGITS
     can
    1.34
    न
    1.14
     in
    1.14
    P
    1.12
    T
    1.09
    M
    1.07
     has
    1.05
     from
    1.04
    C
    1.03
    𝑛
    1.03
    Activations Density 0.091%

    No Known Activations