© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 119024
    Prev
    Next
    INDEX
    Explanations

    diagnostic test evaluation

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

    medical studies discussing diagnostic accuracy or performance of tests and procedures.

    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
    γρά
    -0.85
    сота
    -0.84
    idać
    -0.80
     tazas
    -0.77
    bracket
    -0.77
    δες
    -0.75
    quels
    -0.74
    будь
    -0.74
     мной
    -0.73
     pegatinas
    -0.73
    POSITIVE LOGITS
     sensitivity
    3.02
     Sensitivity
    2.52
    Sensitivity
    2.47
    sensitivity
    2.47
     sensitivities
    2.17
     accuracy
    1.99
     sensibilidad
    1.76
     specificity
    1.73
     sensitive
    1.72
     diagnostic
    1.64
    Activations Density 0.325%

    No Known Activations