© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 29688
    Prev
    Next
    INDEX
    Explanations

    volleyball sport

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ਦਿ
    0.43
    මැ
    0.41
     salesmen
    0.38
     recou
    0.38
    wonder
    0.38
     मर्
    0.38
    runoff
    0.38
    贖
    0.38
    圃
    0.37
    🏦
    0.37
    POSITIVE LOGITS
     volleyball
    1.24
     Volleyball
    1.19
    🏐
    1.05
     volley
    0.93
    volley
    0.75
     FIV
    0.66
     setter
    0.61
    leyball
    0.59
     softball
    0.59
     libero
    0.57
    Activations Density 0.008%

    No Known Activations