© 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. 109513
    Prev
    Next
    INDEX
    Explanations

    foreign words and 'and'

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

    mechanism after systems or model

    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
    '
    0.49
     H
    0.45
     lover
    0.45
    因
    0.44
     fortunes
    0.43
    Vir
    0.43
     highlight
    0.42
     economies
    0.42
    Walker
    0.42
    \[
    0.41
    POSITIVE LOGITS
     நேரத்தில்
    0.55
     теркәлү
    0.54
     بابەت
    0.54
     კომ
    0.52
     vés
    0.52
    稱為
    0.52
    blasts
    0.50
    ంబేద్కర్
    0.49
     prevención
    0.49
     veremos
    0.49
    Activations Density 0.001%

    No Known Activations