© 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. 8403
    Prev
    Next
    INDEX
    Explanations

    antidepressant drugs or poets

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

    the term "antidepressant" and variations of it in medical/pharmaceutical contexts.

    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
     comunica
    -3.05
    replyreport
    -3.05
     retira
    -2.89
    鰨
    -2.84
     书法
    -2.83
    媖
    -2.83
     cathédrale
    -2.78
    
    -2.67
     dedica
    -2.66
     testamento
    -2.64
    POSITIVE LOGITS
    1
    3.42
    4
    3.27
    .
    3.27
    6
    3.22
    2
    3.11
    3
    3.08
    7
    2.91
     to
    2.84
    ，“
    2.78
    s
    2.73
    Activations Density 0.008%

    No Known Activations