© 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. 97847
    Prev
    Next
    INDEX
    Explanations

    scan operations

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

    This neuron detects occurrences of “scan” (or “scanning”) in technical/API contexts.

    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
    &&&
    -0.79
     pavements
    -0.77
    굶
    -0.77
    channelId
    -0.77
     Esti
    -0.77
    انة
    -0.77
    née
    -0.77
    éroport
    -0.76
     SDLK
    -0.75
     clinch
    -0.75
    POSITIVE LOGITS
     Scan
    1.17
    scan
    1.03
     scan
    1.03
    Scan
    1.00
     terapé
    0.82
    divisions
    0.77
     scans
    0.77
    SCAN
    0.75
    SC
    0.75
     sóc
    0.75
    Activations Density 0.011%

    No Known Activations