© 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. 35693
    Prev
    Next
    INDEX
    Explanations

    programming and data analysis code

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

    This neuron fires on code tokens naming functions or API calls (e.g. concat, get_dummies, im2double, mean, std, ST_UNION, roots).

    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
     on
    -1.27
     if
    -1.20
     with
    -1.20
     first
    -1.15
     for
    -1.15
     an
    -1.14
     no
    -1.11
     uses
    -1.10
     esquerda
    -1.09
     Capacidad
    -1.09
    POSITIVE LOGITS
     our
    1.46
     firent
    1.38
     inond
    1.32
    หรือ
    1.30
     maniere
    1.29
     udang
    1.20
     heureuse
    1.16
     applau
    1.15
     Opin
    1.15
     tropicales
    1.13
    Activations Density 0.003%

    No Known Activations