© 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. 84918
    Prev
    Next
    INDEX
    Explanations

    champion or neutral physics

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

    The neuron strongly responds to professional wrestling “title” and “championship” terminology (e.g. champion, championship, reign, defend, AAA Mega Championship).

    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
     which
    -1.62
    着一个
    -1.49
     its
    -1.42
     zupełnie
    -1.28
     kupić
    -1.21
    終於
    -1.19
    ったので
    -1.17
    닌
    -1.17
     Seulement
    -1.16
    取り組
    -1.16
    POSITIVE LOGITS
     on
    1.47
    cía
    1.44
    숯
    1.37
    gelang
    1.37
    袪
    1.34
    võ
    1.30
    legging
    1.30
     様子
    1.29
    scrollView
    1.28
    зраст
    1.28
    Activations Density 0.015%

    No Known Activations