© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 13750
    Prev
    Next
    INDEX
    Explanations

    chemotherapy cancer treatment

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

    mentions of chemotherapy treatments in medical and cancer research contexts.

    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
     These
    -2.34
    ).
    -2.33
     There
    -2.28
    There
    -2.25
     Some
    -2.23
    ’
    -2.20
     Although
    -2.20
    इटम
    -2.19
     So
    -2.17
    This
    -2.16
    POSITIVE LOGITS
    0
    2.88
    .
    2.03
    ጧ
    1.95
     Inſ
    1.95
     новом
    1.94
     mépris
    1.90
     célè
    1.89
     jednej
    1.88
     Conſ
    1.87
    婠
    1.87
    Activations Density 0.042%

    No Known Activations