© 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. 10-GEMMASCOPE-RES-131K
    7. 58490
    Prev
    Next
    INDEX
    Explanations

    cholesterol, sclerosis, filariasis, arrhythmics

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

    medical conditions and disorders, particularly when describing medical terminology.

    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
     you
    -1.73
     with
    -1.57
     a
    -1.48
    ventajas
    -1.28
    初心
    -1.27
    antaranya
    -1.24
     they
    -1.21
    婠
    -1.21
    :['
    -1.20
     into
    -1.18
    POSITIVE LOGITS
     continuó
    1.45
     olmad
    1.37
     powietrza
    1.36
    ਗ਼
    1.31
     [];
    1.31
    </em>
    1.31
     Nachmittag
    1.31
     Lleg
    1.30
     naš
    1.26
    Furthermore
    1.25
    Activations Density 0.823%

    No Known Activations