© 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. 13114
    Prev
    Next
    INDEX
    Explanations

    code, data types, and syntax

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

    The neuron responds to code tokens that are names of data types or classes (identifiers starting with an uppercase letter).

    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
     you
    -1.38
    0
    -1.30
    For
    -1.23
    Just
    -1.13
    //!
    
    -1.12
     a
    -1.09
     takut
    -1.09
    蛀
    -1.06
     блю
    -1.05
     Wikipédia
    -1.05
    POSITIVE LOGITS
    uário
    1.18
    hålla
    1.16
     [])
    1.11
    pkins
    1.05
    Mikro
    1.04
     '\''
    1.03
    いたしました
    1.03
     たい
    1.02
    Джерела
    1.02
     of
    1.02
    Activations Density 0.000%

    No Known Activations