© 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. 78297
    Prev
    Next
    INDEX
    Explanations

    osteomalacia

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

    technical formatting in documents like file headers, legal documents, and medical literature.

    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
    介
    -0.75
    ք
    -0.75
     ト
    -0.72
    lerim
    -0.71
     Estab
    -0.70
    λευ
    -0.69
     chấm
    -0.68
     взе
    -0.68
    vum
    -0.68
    Gold
    -0.66
    POSITIVE LOGITS
     Koh
    0.77
     службы
    0.73
     Kle
    0.68
     Covington
    0.67
    died
    0.67
    xyz
    0.67
     Archive
    0.65
    TypeCode
    0.65
    esthe
    0.64
     archive
    0.64
    Activations Density 0.085%

    No Known Activations