© 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. 66785
    Prev
    Next
    INDEX
    Explanations

    C code keywords and syntax

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

    The neuron fires on literal forward‐slash tokens (e.g. “/”) used in code paths and include directives.

    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
     capitolo
    -1.13
     sentimenti
    -1.08
     aidé
    -1.08
    WAUKEE
    -1.02
     kleinen
    -1.02
     sogni
    -1.00
     écoulé
    -1.00
     policies
    -0.98
     desideri
    -0.98
     beautiful
    -0.98
    POSITIVE LOGITS
    each
    1.04
     soi
    1.02
     tropicales
    1.01
     at
    1.01
     élev
    1.00
     disting
    0.98
    减肥
    0.96
     Concise
    0.96
    icum
    0.96
     Ninh
    0.95
    Activations Density 0.001%

    No Known Activations