© 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. 63737
    Prev
    Next
    INDEX
    Explanations

    cancer invasion and margins

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

    medical terms related to cancer treatment and anatomical pathology, particularly focusing on tumor staging, invasion, and lymph node involvement.

    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
    ləş
    -0.78
    극
    -0.77
     extrêmement
    -0.76
     unfailing
    -0.76
     Failing
    -0.74
     Colonel
    -0.73
     pengusaha
    -0.73
     choisir
    -0.72
    𓆏
    -0.70
     JAN
    -0.70
    POSITIVE LOGITS
     invasion
    1.27
     margins
    1.23
     margin
    1.20
     Invasion
    1.03
    Margins
    1.02
     invaded
    1.01
     positive
    1.00
    margin
    0.93
     invasión
    0.93
    Invasion
    0.91
    Activations Density 0.227%

    No Known Activations