© 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. 118474
    Prev
    Next
    INDEX
    Explanations

    volleyball player

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    孺
    -0.83
    Holstein
    -0.81
    扈
    -0.79
    📲
    -0.76
    uname
    -0.75
    Fabri
    -0.73
     пита
    -0.72
     bara
    -0.72
     Peker
    -0.72
     Yesus
    -0.71
    POSITIVE LOGITS
     volleyball
    1.36
     Volleyball
    1.16
    volley
    1.05
    toolbox
    0.97
     setter
    0.95
     Volley
    0.93
    バレー
    0.91
     нормы
    0.89
    Volley
    0.86
    AVC
    0.85
    Activations Density 0.001%

    No Known Activations