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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 5056
    Prev
    Next
    INDEX
    Explanations

    tickets and entry reservations

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

    entry and admission

    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
    依頼
    0.43
     idealized
    0.43
    Cursors
    0.42
     ചെറു
    0.40
    ંદા
    0.40
    Acet
    0.39
    ϑ
    0.39
     prototyp
    0.39
    諺
    0.38
    喻
    0.38
    POSITIVE LOGITS
     tickets
    2.03
     ticket
    1.91
    tickets
    1.80
     Tickets
    1.77
    Tickets
    1.73
    ticket
    1.71
    チケット
    1.70
     Ticket
    1.66
    Ticket
    1.63
     admission
    1.59
    Activations Density 0.239%

    No Known Activations