© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 12263
    Prev
    Next
    INDEX
    Explanations

    psychology and empiricism

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

    The neuron activates on multi‐word, title‐cased document titles (e.g. book or article names, often including a colon).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tekn
    0.58
    的技术
    0.57
    霰
    0.57
     fusible
    0.56
     Tekn
    0.55
    மார்
    0.53
     技術
    0.53
    ゙
    0.52
    ఆర్
    0.51
    市政
    0.51
    POSITIVE LOGITS
     psychology
    1.70
     Psychology
    1.70
     psicología
    1.60
     psicologia
    1.60
    心理
    1.59
     psychologists
    1.58
    Psych
    1.52
     психо
    1.52
     psychological
    1.51
     psychologist
    1.51
    Activations Density 0.108%

    No Known Activations