© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 15198
    Prev
    Next
    INDEX
    Explanations

    psychology research and MA

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

    The neuron is chiefly triggered by occurrences of “psych”-related terms—that is, words and titles referring to psychology (e.g. psychological, psychologist, psychopathology, Psychology).

    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
     to
    -1.48
     levit
    -1.13
     syk
    -1.11
     yogur
    -1.11
     ribu
    -1.01
     meer
    -1.01
    ֊
    -1.01
     periode
    -1.00
    今度は
    -1.00
     إلى
    -1.00
    POSITIVE LOGITS
     bekämp
    1.13
    kowitz
    1.08
     筋
    1.06
    ঋ
    1.05
    戌
    1.05
     bő
    1.05
    onton
    1.05
    PARED
    1.04
    ğin
    1.03
     spä
    1.03
    Activations Density 0.301%

    No Known Activations