© 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. 82595
    Prev
    Next
    INDEX
    Explanations

    visiting professor, Assistant Professor, scholars

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

    The neuron chiefly detects the word “visiting” (as in “Visiting Professor” or “Visiting Assistant Professor”).

    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
    ファースト
    -0.73
    mender
    -0.71
     fréquent
    -0.68
    ngen
    -0.67
     Pich
    -0.66
    uple
    -0.66
    resti
    -0.66
    resultado
    -0.65
     finding
    -0.65
    Referències
    -0.65
    POSITIVE LOGITS
     unregulated
    0.68
     Жен
    0.66
     Tai
    0.65
    bVar
    0.65
    folg
    0.63
     sumo
    0.63
    าะ
    0.62
     Tail
    0.61
    altered
    0.61
     yakın
    0.60
    Activations Density 0.072%

    No Known Activations