© 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. 102075
    Prev
    Next
    INDEX
    Explanations

    audience behavior at events

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

    speaking softly or raising hand

    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
    两天
    0.47
    几天
    0.43
    FUEL
    0.43
    調理
    0.43
    烹
    0.43
    焚
    0.42
     bbq
    0.41
    깡
    0.41
     BBQ
    0.40
    RIDES
    0.39
    POSITIVE LOGITS
     whispered
    0.80
     whispering
    0.80
     whisper
    0.73
     whispers
    0.73
     seats
    0.71
     attendee
    0.67
     applause
    0.67
     attendees
    0.65
     audience
    0.64
     seating
    0.64
    Activations Density 0.142%

    No Known Activations