© 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. 14907
    Prev
    Next
    INDEX
    Explanations

    end-stage renal disease

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

    technical or scientific terms, particularly in medical, biological, and engineering contexts.

    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
     []:
    -1.37
    tifies
    -1.34
    []
    -1.27
    ibrated
    -1.23
     "..\..\..\
    -1.18
     où
    -1.15
    where
    -1.13
     ....
    -1.12
     we
    -1.10
    çük
    -1.10
    POSITIVE LOGITS
     istimewa
    1.64
     Gemü
    1.33
     menyen
    1.31
    Ƹ
    1.28
     décé
    1.27
     senza
    1.23
     not
    1.23
    槤
    1.22
     normaux
    1.22
     berle
    1.19
    Activations Density 0.186%

    No Known Activations