© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 111200
    Prev
    Next
    INDEX
    Explanations

    breast cancer

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

    mentions of breast cancer or breast-related medical terms in scientific literature.

    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
    ,
    -1.63
     in
    -1.59
     However
    -1.51
    .
    -1.50
    )
    -1.42
    .,
    -1.41
     Some
    -1.38
    );
    -1.36
     Although
    -1.33
     Currently
    -1.32
    POSITIVE LOGITS
     diseños
    1.64
     aparatos
    1.48
     exámenes
    1.48
     tamaños
    1.43
     logros
    1.42
    ⃙
    1.41
     soportes
    1.41
     obstáculos
    1.40
     envíos
    1.40
     breast
    1.38
    Activations Density 0.112%

    No Known Activations