© 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. 34-GEMMASCOPE-RES-131K
    7. 38390
    Prev
    Next
    INDEX
    Explanations

    date picker functionality

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

    This neuron detects programming‐language syntax tokens (e.g. code keywords, delimiters, and punctuation) rather than normal text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     geometri
    -0.77
    startGame
    -0.75
     öppna
    -0.74
     ママ
    -0.74
    發生
    -0.73
     seemed
    -0.73
    дует
    -0.73
    락
    -0.71
     staged
    -0.71
    前回の
    -0.71
    POSITIVE LOGITS
     Calendar
    1.49
     calendar
    1.34
    Calendar
    1.29
     calendars
    1.27
    calendar
    1.23
     calend
    1.11
     CALENDAR
    1.05
     кален
    1.03
     Chrono
    1.02
     Calend
    1.02
    Activations Density 0.030%

    No Known Activations