© 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. 2007
    Prev
    Next
    INDEX
    Explanations

    particular gender, lowest order

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

    rough estimate

    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
    Alongside
    0.38
     soltanto
    0.34
     পুরোনো
    0.31
     нередко
    0.30
    🤝
    0.30
     ✨
    0.29
     Evidently
    0.29
    🙈
    0.29
     .{
    0.29
    ऱ्या
    0.28
    POSITIVE LOGITS
     visage
    0.63
     heretofore
    0.57
     maladies
    0.56
     environs
    0.56
     ilk
    0.55
     angst
    0.55
     promulgating
    0.52
     subter
    0.51
     procl
    0.50
     purview
    0.49
    Activations Density 1.239%

    No Known Activations