© 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. 10-GEMMASCOPE-RES-131K
    7. 67044
    Prev
    Next
    INDEX
    Explanations

    body systems and health

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

    health-related terms such as "immune system," "brain health," "hormones," "metabolism," and "blood flow."

    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
     such
    -1.88
     that
    -1.84
     it
    -1.68
     or
    -1.45
     Zuhause
    -1.45
     beeindruck
    -1.40
     juzg
    -1.37
     różne
    -1.35
     talentos
    -1.33
     genellikle
    -1.33
    POSITIVE LOGITS
     and
    1.48
     الجميع
    1.28
     paradis
    1.28
     &
    1.27
    気で
    1.24
     duran
    1.23
    w
    1.20
    !
    1.20
    },
    1.20
    Thing
    1.16
    Activations Density 0.063%

    No Known Activations