© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 6800
    Prev
    Next
    INDEX
    Explanations

    seizures and convulsions

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

    medical terms related to seizures and neurological disorders.

    oai_token-act-pair · claude-3-7-sonnet-20250219
    Triggered 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
    Negative Logits
    BUT
    -1.42
    
    -1.38
    (
    -1.36
    يتي
    -1.34
    وله
    -1.23
    杀了
    -1.23
     BUT
    -1.23
     instead
    -1.22
     econômica
    -1.22
     málaga
    -1.20
    POSITIVE LOGITS
     amikor
    1.28
    咘
    1.26
     ПОД
    1.25
    raseña
    1.22
    rália
    1.22
    数百
    1.21
     poslední
    1.20
     mindig
    1.20
    They
    1.20
    数十
    1.19
    Activations Density 0.120%

    No Known Activations