© 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. 99320
    Prev
    Next
    INDEX
    Explanations

    play sport or game

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

    The neuron detects occurrences of the word “play” (the verb “play,” in any casing) in the text.

    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
    CHREIB
    -2.59
    '
    -2.55
     Their
    -2.50
    lgari
    -2.47
    鹇
    -2.44
    锨
    -2.41
    öpfer
    -2.39
    逦
    -2.36
    H
    -2.34
    ально
    -2.33
    POSITIVE LOGITS
    {
    3.44
    e
    3.44
    or
    2.89
    หรือ
    2.69
    p
    2.64
     питання
    2.47
    ).
    2.45
    一個
    2.41
    或
    2.36
    iapkan
    2.33
    Activations Density 0.023%

    No Known Activations