© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 43220
    Prev
    Next
    INDEX
    Explanations

    psychology, psychological

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

    The neuron detects occurrences of psychology‐related terms (words containing the “psycholog” root).

    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
     in
    -1.99
     How
    -1.98
     the
    -1.98
     They
    -1.80
     Why
    -1.77
     Including
    -1.77
    t
    -1.75
     If
    -1.73
     When
    -1.73
     Of
    -1.68
    POSITIVE LOGITS
     Bretaña
    1.89
     cimetière
    1.77
     dimanche
    1.71
     dîner
    1.70
     покупать
    1.60
     courir
    1.59
     escalier
    1.59
    גם
    1.58
     culte
    1.55
     botines
    1.54
    Activations Density 0.013%

    No Known Activations