© 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. 102574
    Prev
    Next
    INDEX
    Explanations

    hemiplegia, apoplexy, ophthalmoplegia

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

    medical condition terms, particularly those related to neurological disorders and physical symptoms of diseases.

    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
     to
    -1.86
    '
    -1.76
     anxiously
    -1.41
    獃
    -1.39
    er
    -1.39
     xxiii
    -1.38
    </h2>
    -1.34
     
    -1.33
     frantically
    -1.31
     habitually
    -1.30
    POSITIVE LOGITS
     uzyskać
    1.63
     berücksichtigen
    1.62
     різних
    1.49
     якості
    1.48
     öffentliche
    1.47
     komplette
    1.45
     Menurut
    1.42
    
    1.42
     obiet
    1.40
     originalen
    1.40
    Activations Density 0.115%

    No Known Activations