© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 163845
    Prev
    Next
    INDEX
    Explanations

    entertaining others or oneself

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

    providing entertainment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    '
    0.67
    齜
    0.65
     mít
    0.63
    م
    0.62
    的的
    0.61
    س
    0.59
    ोर
    0.58
    О
    0.56
     htt
    0.55
    و
    0.54
    POSITIVE LOGITS
    entertain
    1.04
    entertainment
    1.03
     entertainment
    0.96
     Entertainment
    0.96
    Entertainment
    0.90
     Entertain
    0.88
     entertained
    0.88
     entertain
    0.88
     entertaining
    0.86
    tainment
    0.83
    Activations Density 0.026%

    No Known Activations