© 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. 113955
    Prev
    Next
    INDEX
    Explanations

    vehicle wheels

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

    This neuron detects mentions of “wheel”/“wheels” (the word “wheels” and its singular/plural 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
    ↵
    -2.73
     you
    -2.48
    $
    -2.28
    庒
    -2.25
     they
    -2.20
    衪
    -2.16
    捭
    -2.13
    蕯
    -2.13
    桖
    -2.11
     можешь
    -2.09
    POSITIVE LOGITS
    凩
    3.33
    玙
    2.55
    𓆜
    2.53
     Wheels
    2.52
    ໊
    2.50
    鈇
    2.41
     brinde
    2.41
     besonder
    2.34
    縢
    2.33
    暃
    2.30
    Activations Density 0.003%

    No Known Activations