© 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. 116590
    Prev
    Next
    INDEX
    Explanations

    health hazards and diseases

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

    medical and health risks associated with toxic substances, pollutants, and diseases.

    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
    niczka
    -0.80
    ؤ
    -0.79
    glected
    -0.78
    liston
    -0.78
     rodzin
    -0.77
    äft
    -0.76
     purpure
    -0.76
    探索
    -0.74
    ÉS
    -0.73
    زد
    -0.73
    POSITIVE LOGITS
     reproductive
    1.20
     Effects
    1.17
     DNA
    1.16
     effects
    1.11
    Effects
    1.11
     neurological
    0.96
    wildlife
    0.95
    effects
    0.93
     fertility
    0.92
     Symptoms
    0.90
    Activations Density 0.066%

    No Known Activations