© 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. 182375
    Prev
    Next
    INDEX
    Explanations

    travel, sports events, or phases

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

    sports and games

    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
    ther
    0.45
    vital
    0.45
    amount
    0.44
    ‘
    0.44
    sapp
    0.44
    '
    0.42
    arger
    0.42
    tor
    0.42
    need
    0.41
     dynamism
    0.41
    POSITIVE LOGITS
     preseason
    0.58
     jogadores
    0.58
    这场
    0.56
    赛季
    0.55
     celebrate
    0.54
    🏒
    0.52
     فوټبال
    0.50
    此事
    0.50
     старосног
    0.50
     जश्न
    0.50
    Activations Density 0.002%

    No Known Activations