© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 68427
    Prev
    Next
    INDEX
    Explanations

    reel, reels

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

    The neuron specifically detects occurrences of the word “reel” (and its plural or capitalized variants).

    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
    
    -2.75
    ↵↵
    -2.73
    ஂ
    -2.70
    1
    -2.56
     Würde
    -2.47
     lurking
    -2.44
     \
    -2.39
    ৄ
    -2.36
     About
    -2.27
     weary
    -2.27
    POSITIVE LOGITS
    木坂
    2.72
    ’，
    2.70
    '
    2.67
    🍺
    2.63
    ⬇
    2.59
    🥳
    2.56
    ❗
    2.55
    ！”
    2.47
    🎉
    2.44
    👀
    2.42
    Activations Density 0.002%

    No Known Activations