© 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. 10-GEMMASCOPE-RES-131K
    7. 21844
    Prev
    Next
    INDEX
    Explanations

    psychopathy and psychopharmacology

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

    words related to psychology and psychiatric conditions, particularly focusing on terms like "psychopathy," "psychotic," and "psychopharmacology."

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron activates strongly on any occurrence of the substring “psych” (as in psychopathy, psychotic, psychopath, etc.).

    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
    ⮑
    -1.95
    ates
    -1.80
    
    -1.79
    感は
    -1.78
    􀂃
    -1.73
    人是
    -1.73
    嫫
    -1.70
    ſhip
    -1.66
    先は
    -1.66
    étais
    -1.65
    POSITIVE LOGITS
    .
    2.66
    the
    2.08
    }
    2.05
    1.79
    7
    1.64
    if
    1.63
    %
    1.57
    сті
    1.49
     if
    1.48
    but
    1.48
    Activations Density 0.020%
    No Known Activations