Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 8161
    Prev
    Next
    INDEX
    Explanations

    blood cancer diagnoses

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

    medical and technical terminology, particularly related to leukemia and software code.

    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
    vable
    -0.75
     repatriation
    -0.68
    ổng
    -0.67
    Fiction
    -0.67
    bili
    -0.66
     penet
    -0.65
    seller
    -0.65
    otation
    -0.64
    原创
    -0.63
     CBA
    -0.63
    POSITIVE LOGITS
    minecraft
    0.78
     barriga
    0.77
     Braunschweig
    0.76
    パック
    0.75
     launchers
    0.75
    ohjel
    0.74
     episode
    0.73
    quante
    0.73
     inches
    0.73
     배
    0.72
    Activations Density 0.034%

    No Known Activations