© 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. 31-GEMMASCOPE-2-RES-262K
    7. 139137
    Prev
    Next
    INDEX
    Explanations

    non-English words

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

    invoice document presentation

    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_31_width_262k_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
     kits
    0.50
    0.49
    *
    0.47
     all
    0.44
     ud
    0.43
     ion
    0.43
    -
    0.43
    ↵
    0.43
     $
    0.42
    param
    0.42
    POSITIVE LOGITS
     ഇപ്പോള്‍
    0.54
    <unused41>
    0.53
     пассажи
    0.53
    韪
    0.52
     તેઓ
    0.51
    щий
    0.50
    <unused46>
    0.49
    Clientes
    0.49
    épid
    0.48
     fréquente
    0.48
    Activations Density 0.001%

    No Known Activations