© 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. 31-GEMMASCOPE-2-RES-262K
    7. 71115
    Prev
    Next
    INDEX
    Explanations

    packets, events, incoming signals

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

    event handling and dispatch

    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
    Negative Logits
    deployRoot
    0.45
    ơm
    0.43
    UTICAL
    0.43
    ༠
    0.42
     হাইড্রোজেন
    0.42
    構築
    0.41
    öp
    0.41
     изго
    0.41
    氫
    0.41
     シュ
    0.41
    POSITIVE LOGITS
    事件
    1.06
     события
    0.98
     eventos
    0.95
     events
    0.91
     eventi
    0.91
     Events
    0.90
     peristiwa
    0.90
     Event
    0.90
    events
    0.90
     事件
    0.90
    Activations Density 0.079%

    No Known Activations