© 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. 64184
    Prev
    Next
    INDEX
    Explanations

    high prevalence areas

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

    geographical descriptions of disease endemic areas.

    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
    декват
    -0.89
     barri
    -0.83
     antem
    -0.82
     alpin
    -0.82
    raad
    -0.81
     gutt
    -0.81
    エム
    -0.81
     rotund
    -0.80
    ingroup
    -0.80
    
    -0.79
    POSITIVE LOGITS
     risk
    1.86
     areas
    1.85
     high
    1.77
     zone
    1.42
     zones
    1.39
     area
    1.29
     prone
    1.29
     risky
    1.27
     red
    1.27
    risk
    1.27
    Activations Density 0.074%

    No Known Activations