© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 84240
    Prev
    Next
    INDEX
    Explanations

    medical disease context

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

    content in formal articles or news reports, particularly focusing on substantive body text.

    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
    FUENTES
    -1.37
     włosów
    -1.36
     stadion
    -1.29
    titleMargin
    -1.23
     homicidio
    -1.22
     graisse
    -1.20
    ฅ
    -1.18
    Œuvres
    -1.17
     permitió
    -1.16
     menganggap
    -1.16
    POSITIVE LOGITS
     "@/
    1.16
     креди
    1.13
     '@/
    1.13
    aben
    1.09
    🩹
    1.08
    𝜓
    1.06
     detergente
    1.06
    J
    1.05
    ，
    1.05
     نوجوان
    1.04
    Activations Density 0.007%

    No Known Activations