© 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. 22-GEMMASCOPE-RES-131K
    7. 65746
    Prev
    Next
    INDEX
    Explanations

    medical context, quantities, or qualifications

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

    words that might appear in formal texts like legal documents, technical papers, or academic writing.

    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_22/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
    ↵↵
    -2.17
     '
    -1.98
     The
    -1.91
    ところに
    -1.91
     If
    -1.77
     it
    -1.75
     and
    -1.63
     แต่
    -1.63
     正面
    -1.62
     AFTER
    -1.61
    POSITIVE LOGITS
    鸶
    2.50
    تحميل
    2.11
    नलोड
    2.02
    iamo
    2.00
    стреча
    1.99
    骉
    1.98
    Напомним
    1.94
    蛧
    1.94
    ppings
    1.91
    licitations
    1.90
    Activations Density 0.149%

    No Known Activations