© 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. 102278
    Prev
    Next
    INDEX
    Explanations

    Psychiatry and concomitant disease

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

    The neuron activates for words related to the field of psychiatry, including "psychiatrist," "psychiatry," and related mental health terminology.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    ↵↵
    -2.44
     смерть
    -1.97
    两位
    -1.95
     Russland
    -1.93
     возможность
    -1.93
    こんばんは
    -1.91
    蔔
    -1.90
    ly
    -1.88
    *
    -1.88
    硖
    -1.83
    POSITIVE LOGITS
    y
    3.95
    ing
    2.81
    쨩
    2.70
    3
    2.48
     It
    2.47
    4
    2.45
    7
    2.42
    棪
    2.41
     feiert
    2.41
    䊏
    2.39
    Activations Density 0.005%

    No Known Activations