© 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. 71627
    Prev
    Next
    INDEX
    Explanations

    public health policy

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

    terms related to "public health" and public policy areas.

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

    The neuron activates on occurrences of the word “public” (in any context or casing).

    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
    ৢ
    -1.75
     alguns
    -1.73
     lokalen
    -1.70
     our
    -1.69
    borsa
    -1.66
     económicas
    -1.65
     kürzlich
    -1.65
    딕
    -1.54
     füh
    -1.50
     históricas
    -1.50
    POSITIVE LOGITS
     and
    2.73
    nių
    1.62
    面的
    1.51
    ）　
    1.36
    ַּ
    1.27
     
    1.27
    🎃
    1.27
    蒾
    1.25
     lengu
    1.23
    jestel
    1.22
    Activations Density 0.022%

    No Known Activations