© 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. 34-GEMMASCOPE-RES-131K
    7. 93471
    Prev
    Next
    INDEX
    Explanations

    medical conditions and adverse events

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

    conditions, illnesses, or negative health events like injuries, medical emergencies, or disabilities.

    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
     absur
    -0.85
     Sos
    -0.84
     Defic
    -0.80
     CHA
    -0.79
    亵
    -0.77
    ZZZZ
    -0.75
     frustrations
    -0.75
    氤
    -0.75
    ראות
    -0.74
    ◼
    -0.74
    POSITIVE LOGITS
     illness
    2.89
     sickness
    2.13
     health
    1.96
     medical
    1.91
     injury
    1.86
     Illness
    1.83
     illnesses
    1.68
     disease
    1.66
     death
    1.64
     job
    1.62
    Activations Density 0.051%

    No Known Activations