© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 17697
    Prev
    Next
    INDEX
    Explanations

    bec, beck, or Бес

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

    bet365

    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_53_width_65k_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
    ℹ
    0.40
    ivariable
    0.39
    வில
    0.39
     wyją
    0.38
     kammam
    0.37
    幼稚
    0.37
    udal
    0.37
    ÷
    0.37
    στ
    0.36
     aktiv
    0.35
    POSITIVE LOGITS
    BEC
    0.57
     bec
    0.54
    beck
    0.54
    бек
    0.53
    বে
    0.52
     BEC
    0.52
    bek
    0.48
     Beckett
    0.48
    بك
    0.48
    বেক
    0.48
    Activations Density 0.007%

    No Known Activations