© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 47028
    Prev
    Next
    INDEX
    Explanations

    clinical and health outcomes

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

    words and phrases related to medical or clinical outcomes.

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

    The neuron fires on words that describe results or outcomes—especially positive or evaluative terms like “improve,” “outcome,” “best,” and “successful.”

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408
    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
    Negative Logits
    
    -0.92
    Alguien
    -0.75
    простра
    -0.75
    
    -0.73
    estial
    -0.71
    埛
    -0.71
    ūnas
    -0.70
    getCause
    -0.70
    ndorf
    -0.69
    нін
    -0.69
    POSITIVE LOGITS
     outcome
    5.81
     outcomes
    5.44
    outcome
    4.31
    Outcome
    4.03
     Outcome
    4.00
     Outcomes
    3.88
    outcomes
    3.81
    Outcomes
    3.47
     OUTCOMES
    3.14
     result
    2.73
    Activations Density 0.180%

    No Known Activations