© 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. 65465
    Prev
    Next
    INDEX
    Explanations

    combine management

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

    The neuron detects section headers or title-like phrases (e.g. document titles, report headings, copyright notices, 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_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
     Tyne
    -0.81
    =$((
    -0.80
     indisponible
    -0.76
     assignee
    -0.75
     announcer
    -0.72
    itized
    -0.72
    Estimating
    -0.72
    doms
    -0.71
     ontology
    -0.71
     Estimating
    -0.69
    POSITIVE LOGITS
    Combine
    0.93
    combine
    0.78
    Combining
    0.77
    audi
    0.76
     Combine
    0.75
    BASIC
    0.75
    Management
    0.73
     combining
    0.73
     Mange
    0.72
    RSI
    0.72
    Activations Density 0.004%

    No Known Activations