© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 7500
    Prev
    Next
    INDEX
    Explanations

    draw, raffle, bingo, results

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

    The neuron fires on occurrences of the word “draw” or “drawing” (including related contexts like “lot drawing” or numbered draw headings).

    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
    6
    -1.92
    9
    -1.70
     في
    -1.62
    z
    -1.60
    7
    -1.59
    2
    -1.55
    一定
    -1.52
    f
    -1.50
    de
    -1.48
    8
    -1.48
    POSITIVE LOGITS
     for
    1.49
     pincel
    1.47
    ulipas
    1.46
    yym
    1.38
     poderos
    1.35
     handful
    1.34
     there
    1.34
    homonymie
    1.33
     bijzonder
    1.32
     sorteo
    1.31
    Activations Density 0.014%

    No Known Activations