© 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. 79063
    Prev
    Next
    INDEX
    Explanations

    onco, onco-, onco-lytic

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

    scientific names or terminology related to organisms and diseases, particularly parasites and oncology terms.

    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
    我们的
    -0.84
     Erklärung
    -0.77
    しようと
    -0.75
    𖥻
    -0.75
     plaît
    -0.74
     можно
    -0.71
     Autre
    -0.70
    ческую
    -0.70
     пользователем
    -0.69
    Counter
    -0.69
    POSITIVE LOGITS
    ions
    1.01
    新人
    0.84
    Imports
    0.82
    cademia
    0.81
    nion
    0.79
    hynchus
    0.79
    ciale
    0.77
     continúas
    0.74
     Gastro
    0.74
    iony
    0.74
    Activations Density 0.045%

    No Known Activations