© 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. 59228
    Prev
    Next
    INDEX
    Explanations

    health and knowledge

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

    words and phrases related to human-made objects, products, or physical systems.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    This neuron fires on mentions of health—i.e. when the text is discussing health or health-related matters.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    </em>
    -2.00
    ≫
    -1.54
     S
    -1.44
    abinieri
    -1.36
    ensä
    -1.35
    aryti
    -1.35
    </h2>
    -1.34
    omenclature
    -1.30
     dicha
    -1.30
    pushFollow
    -1.29
    POSITIVE LOGITS
     decorativas
    1.42
    今でも
    1.32
     florales
    1.28
    atific
    1.28
     tatuaje
    1.26
    别人
    1.26
    PTEMBER
    1.21
    惫
    1.20
     decorativos
    1.20
     usados
    1.20
    Activations Density 0.074%

    No Known Activations