© 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. 34-GEMMASCOPE-RES-131K
    7. 2208
    Prev
    Next
    INDEX
    Explanations

    psychiatric conditions and treatments

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

    medical and psychiatric research terminology, especially related to clinical studies and mental health disorders.

    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_34/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
    alige
    -0.91
     Physio
    -0.87
     Perio
    -0.86
     physiotherapy
    -0.82
    Physics
    -0.79
    தே
    -0.76
     проходи
    -0.73
    ディズニー
    -0.71
     Physics
    -0.70
     Haushalts
    -0.70
    POSITIVE LOGITS
     psychiatrists
    1.70
     psychiatric
    1.67
     Psychiatry
    1.65
     psychiatry
    1.63
     suicide
    1.59
    psychiat
    1.55
     psiqui
    1.53
    Psychiat
    1.52
     psychiatrist
    1.52
     antidepress
    1.52
    Activations Density 0.481%

    No Known Activations