© 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. 66770
    Prev
    Next
    INDEX
    Explanations

    foreign language code

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

    The neuron is highly activated by numeric literal tokens (i.e. numbers) in code.

    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
     whole
    -1.08
     otros
    -1.07
     други
    -1.00
    terreno
    -0.95
     einige
    -0.95
     wood
    -0.94
     других
    -0.94
     others
    -0.93
     όλα
    -0.93
    時間は
    -0.91
    POSITIVE LOGITS
    zetek
    1.01
    istungs
    1.01
     ГА
    0.95
     (
    0.93
    anadas
    0.93
    ñó
    0.89
     КА
    0.88
    презента
    0.87
     Langen
    0.87
    çou
    0.86
    Activations Density 0.009%

    No Known Activations