© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 65397
    Prev
    Next
    INDEX
    Explanations

    martial arts (judo, karate, taekwondo)

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

    The main thing this neuron does is detect terms related to martial arts and combat disciplines.

    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
     the
    -1.62
     recommande
    -1.48
     revelado
    -1.39
     penas
    -1.38
    mpagne
    -1.38
     cerveja
    -1.37
     hermoso
    -1.35
     refreshToken
    -1.34
     rafra
    -1.34
    鋲
    -1.34
    POSITIVE LOGITS
     karate
    1.80
    ！”
    1.77
    ”,
    1.64
    。”
    1.62
    ?”
    1.53
    .”
    1.50
    ekwondo
    1.48
    ”、“
    1.47
     используя
    1.40
    ulação
    1.37
    Activations Density 0.022%

    No Known Activations