© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 15079
    Prev
    Next
    INDEX
    Explanations

    renal, thyroid, medical procedures

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

    words related to technical or industrial domains, particularly body parts, organs, or equipment.

    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_10/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
     получает
    -1.35
    腘
    -1.31
     принимает
    -1.22
    鵙
    -1.19
    檮
    -1.19
    knows
    -1.18
    几分
    -1.15
    
    -1.15
     adik
    -1.15
     lâ
    -1.15
    POSITIVE LOGITS
     other
    2.25
     otros
    1.68
    </h1>
    1.50
     otras
    1.48
    其他
    1.44
     another
    1.43
     другим
    1.42
     மற்ற
    1.41
    อื่น
    1.36
     and
    1.31
    Activations Density 0.554%

    No Known Activations