© 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. 34-GEMMASCOPE-RES-131K
    7. 59152
    Prev
    Next
    INDEX
    Explanations

    gymnastic actions and performance

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

    This neuron identifies the names of gymnastic or exercise movements (e.g. “kip,” “tuck jump,” “dive bomb,” “hanging knee raise,” etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    resposta
    -1.00
    jados
    -0.81
     Ard
    -0.73
    bof
    -0.72
     apple
    -0.72
    formin
    -0.71
    =”
    -0.69
     pom
    -0.69
    IA
    -0.68
    Pom
    -0.68
    POSITIVE LOGITS
    Siri
    0.85
     Siri
    0.82
     attempts
    0.82
    ហ
    0.80
     skill
    0.79
    skill
    0.77
     difficulty
    0.77
     attempted
    0.76
     газе
    0.76
     ingår
    0.76
    Activations Density 0.005%

    No Known Activations