© 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. 67901
    Prev
    Next
    INDEX
    Explanations

    It takes

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

    The neuron fires on standalone numeric literals (numbers appearing in equations or as numeric results).

    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
    猹
    -2.78
     rése
    -2.77
     parachoque
    -2.66
    besondere
    -2.59
     valentín
    -2.48
    ୌ
    -2.48
    
    -2.44
     hiver
    -2.44
     habile
    -2.42
     blessures
    -2.41
    POSITIVE LOGITS
    </strong>
    3.50
     to
    2.75
    y
    2.73
    al
    2.52
     “
    2.48
    {
    2.48
     owing
    2.39
    ↵
    2.34
    by
    2.31
     ‘
    2.31
    Activations Density 0.002%

    No Known Activations