© 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. 128754
    Prev
    Next
    INDEX
    Explanations

    biliary disease

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

    first and last names of people, particularly when they appear together.

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

    The neuron activates on tokens containing the letter sequence “ill.”

    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
    TryDecode
    -2.55
    ㌧
    -2.53
     STILL
    -2.44
    ignent
    -2.39
    鐧
    -2.36
     särskilt
    -2.36
     äls
    -2.33
     liknande
    -2.30
    béco
    -2.30
    licité
    -2.30
    POSITIVE LOGITS
    {
    3.83
    $
    2.89
    ',
    2.61
    <
    2.61
    [
    2.48
    for
    2.42
    e
    2.39
    )
    2.34
    ,’
    2.33
    </strong>
    2.31
    Activations Density 0.004%

    No Known Activations