© 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. 10-GEMMASCOPE-RES-131K
    7. 59967
    Prev
    Next
    INDEX
    Explanations

    division into groups

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

    This neuron detects mentions of how study subjects are divided into numbered groups (e.g. “four groups based on …,” “six age groups,” etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    en
    -1.47
    begin
    -1.45
     on
    -1.41
    Why
    -1.39
     in
    -1.30
    D
    -1.30
    ve
    -1.23
     time
    -1.23
    M
    -1.21
    to
    -1.20
    POSITIVE LOGITS
     olika
    1.52
    Màu
    1.42
    淠
    1.41
     uyt
    1.38
    inWeight
    1.37
    趼
    1.36
    
    1.32
     llor
    1.30
     choses
    1.30
    partie
    1.30
    Activations Density 0.052%

    No Known Activations