© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 75322
    Prev
    Next
    INDEX
    Explanations

    treatments and solutions

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

    medical and scientific treatment descriptions in informational or technical contexts.

    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
     inoltre
    -1.29
     médec
    -1.21
    ınıza
    -1.12
    ınızı
    -1.11
     цього
    -1.10
     này
    -1.10
     malades
    -1.10
     ayrıca
    -1.10
    ERVER
    -1.09
    Oso
    -1.09
    POSITIVE LOGITS
     by
    1.53
     rather
    1.43
     verschiedene
    1.35
     its
    1.32
     to
    1.30
     but
    1.23
     instead
    1.22
     solution
    1.20
     її
    1.15
    ;
    1.13
    Activations Density 0.461%

    No Known Activations