© 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. 31306
    Prev
    Next
    INDEX
    Explanations

    bladder cancer

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

    terminology and concepts related to bladder and urinary tract medical conditions.

    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
    lipe
    -0.88
     angin
    -0.77
     capital
    -0.76
     Schar
    -0.73
    畑
    -0.72
    tilo
    -0.71
     air
    -0.69
     Taunton
    -0.68
    Ле
    -0.68
    👑
    -0.68
    POSITIVE LOGITS
     bladder
    2.31
     Bladder
    2.05
    bladder
    1.80
    膀
    1.57
     uro
    1.52
     Uro
    1.48
    Uro
    1.34
     urinary
    1.30
     urethra
    1.15
     urine
    1.13
    Activations Density 0.213%

    No Known Activations