© 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
    5. 40-GEMMASCOPE-2-RES-16K
    7. 9242
    Prev
    Next
    INDEX
    Explanations

    Sydney, Taipei, Vietnam, Arthur, Worship

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

    go to

    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_40_width_16k_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
     però
    0.52
     lekin
    0.50
    但是在
    0.47
     lakini
    0.46
     சாப்பிட
    0.45
    霎
    0.45
     spät
    0.44
     σημ
    0.43
     แต่
    0.42
     speculator
    0.42
    POSITIVE LOGITS
     Z
    0.52
     Уже
    0.50
    Zhou
    0.48
     Zhou
    0.48
     Young
    0.47
     Yamaguchi
    0.47
     यंग
    0.47
    Wood
    0.46
     Williams
    0.44
    Young
    0.44
    Activations Density 0.179%

    No Known Activations