© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 8178
    Prev
    Next
    INDEX
    Explanations

    our comfortable seats

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

    stadium spectators cheering

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

    stadium

    np_max-act-logits · claude-4-5-sonnet
    Triggered by @sk5695
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_40_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    考核
    0.44
     deterministic
    0.43
    ிறேன்
    0.43
     Michaelmas
    0.43
    瀚
    0.43
     Fhir
    0.43
     proliferative
    0.42
     Wittgenstein
    0.42
     atelier
    0.41
    翰
    0.41
    POSITIVE LOGITS
     stadium
    1.53
     स्टेडियम
    1.35
     stadion
    1.35
     Stadium
    1.31
    Stadium
    1.23
     stadiums
    1.22
     estadio
    1.16
     Stadion
    1.12
     seats
    1.02
    🏟
    1.02
    Activations Density 0.310%

    No Known Activations