© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 64523
    Prev
    Next
    INDEX
    Explanations

    verb endings followed by nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    為に
    -1.10
     However
    -1.08
     mehr
    -1.07
     beinahe
    -1.06
    這裡
    -1.05
    ⌗
    -1.04
    以下是
    -1.02
     शुर
    -0.99
     nahezu
    -0.99
     dlouho
    -0.98
    POSITIVE LOGITS
     also
    1.56
     in
    1.32
    自己的
    1.23
     granat
    1.17
     something
    1.15
    自己
    1.14
     entire
    1.13
    ंप
    1.12
    ‌اند
    1.08
    <>
    1.08
    Activations Density 0.019%

    No Known Activations