© 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. 14951
    Prev
    Next
    INDEX
    Explanations

    stadiums and specific venues

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

    stadium, park, theatre, stage, center

    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
     psychosocial
    0.49
     Elektrokhimiya
    0.49
     Deuter
    0.48
     CNRS
    0.47
     Psychological
    0.47
     मनोवैज्ञानिक
    0.47
     Issled
    0.46
    苒
    0.46
     hyperemia
    0.46
     deuteron
    0.46
    POSITIVE LOGITS
     stadiums
    1.38
     stadium
    1.38
    🏟
    1.31
     Stadium
    1.30
    Stadium
    1.28
     स्टेडियम
    1.21
     estadio
    1.18
     stadion
    1.16
     Stadion
    0.98
     Estadio
    0.95
    Activations Density 0.079%

    No Known Activations