© 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. 104306
    Prev
    Next
    INDEX
    Explanations

    assigned groups, questions, phases

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

    This neuron detects structured enumeration labels—such as numbered “series I, II, III,” type identifiers (“type A granule”), roman‐numeral or parenthetical numbering markers used to organize experimental groups or sections.

    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
    stums
    -1.15
    HttpHeaders
    -1.02
    作战
    -0.98
     叶子
    -0.98
    dorff
    -0.97
    viembre
    -0.96
    WidgetItem
    -0.95
    TableColumn
    -0.92
    anyika
    -0.91
    wski
    -0.91
    POSITIVE LOGITS
    摆手
    1.21
    んでる
    1.11
    cach
    1.02
     passende
    1.01
     vår
    1.01
     väljer
    1.00
     bohat
    0.97
     zako
    0.97
     technische
    0.97
    ไม่มี
    0.96
    Activations Density 0.000%

    No Known Activations