© 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. 22-GEMMASCOPE-RES-131K
    7. 64851
    Prev
    Next
    INDEX
    Explanations

    disease resolution and recovery

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

    medical cases describing successful treatment outcomes and disease remission.

    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_22/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
     aktiviert
    -1.20
     gemakkelijk
    -1.02
     eenvou
    -1.02
     miljoner
    -0.99
     секунд
    -0.98
     создания
    -0.97
     ögon
    -0.97
     افزایش
    -0.96
     fenêtres
    -0.95
     peindre
    -0.95
    POSITIVE LOGITS
     after
    1.46
     improved
    1.41
     success
    1.30
     months
    1.28
     improvement
    1.26
    felizmente
    1.23
     completely
    1.23
     improvements
    1.20
     weeks
    1.19
     gradually
    1.16
    Activations Density 0.087%

    No Known Activations