© 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. 95646
    Prev
    Next
    INDEX
    Explanations

    medical conditions and cells

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

    medical and scientific terminology for diseases, chemicals, and biological structures.

    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
    了什么
    -1.44
     negó
    -1.29
     pidió
    -1.29
     recordó
    -1.26
    pecified
    -1.25
    agerie
    -1.24
     LIABLE
    -1.20
     advirtió
    -1.20
    ඈ
    -1.19
     advierte
    -1.16
    POSITIVE LOGITS
     has
    1.41
     (
    1.22
    近年来
    1.11
     in
    1.09
    Usually
    1.07
     یکی
    1.03
     honom
    1.02
    Juli
    1.00
    These
    1.00
    很多
    1.00
    Activations Density 0.689%

    No Known Activations