© 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-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 54681
    Prev
    Next
    INDEX
    Explanations

    native speakers or locals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    лье
    0.42
    意
    0.40
     toutes
    0.40
    Diffuse
    0.40
    菁
    0.40
    льно
    0.38
    Φ
    0.38
    ャ
    0.38
    め
    0.38
    少数
    0.38
    POSITIVE LOGITS
     insiders
    0.72
     actual
    0.72
    実際に
    0.70
    actual
    0.67
    实际
    0.63
    實際
    0.61
     insider
    0.60
     locals
    0.59
     aktual
    0.59
     실제
    0.59
    Activations Density 0.048%

    No Known Activations