© 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. 315
    Prev
    Next
    INDEX
    Explanations

    health conditions or processes

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

    terms related to medical conditions, symptoms, and diseases in scientific or health content.

    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
     and
    -1.41
     or
    -1.35
     now
    -1.30
     will
    -1.21
     would
    -1.20
     one
    -1.19
     to
    -1.18
     perhaps
    -1.18
    conceito
    -1.16
     out
    -1.16
    POSITIVE LOGITS
    がありますが
    1.63
    撅
    1.34
     suure
    1.34
     défauts
    1.30
     centru
    1.24
     dignité
    1.23
     conster
    1.23
     rafraî
    1.23
    ihnachts
    1.22
    点点头
    1.22
    Activations Density 0.119%

    No Known Activations