© 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. 34-GEMMASCOPE-RES-131K
    7. 49793
    Prev
    Next
    INDEX
    Explanations

    ICD-10 tenth revision

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

    classification system references like ISBN, ICD-10, and DSM classifications in medical and publishing 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_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
    ørs
    -0.79
    quarters
    -0.76
     Message
    -0.75
     Ն
    -0.75
     sâ
    -0.75
     Blom
    -0.74
    Light
    -0.73
    inator
    -0.73
     partes
    -0.72
     HK
    -0.71
    POSITIVE LOGITS
     ten
    1.41
    Ten
    1.17
     Tenth
    1.16
     десять
    1.13
     zehn
    1.13
     Ten
    1.13
     tenth
    1.04
    十
    1.01
     TEN
    0.93
     Eleventh
    0.91
    Activations Density 0.031%

    No Known Activations