© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 11549
    Prev
    Next
    INDEX
    Explanations

    some, certain, one, someone, something

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

    specifying relationships or thresholds

    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_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    苌
    0.44
    淢
    0.43
    🖒
    0.43
    Ϲ
    0.41
     குழந்தைகளின்
    0.40
     многочис
    0.40
     кар
    0.40
     судо
    0.39
     शासकीय
    0.39
    𝒽
    0.39
    POSITIVE LOGITS
    某
    0.72
    某个
    0.65
     suatu
    0.51
    某一
    0.50
     another
    0.45
     oneself
    0.44
     jednego
    0.43
     something
    0.42
     someone
    0.42
     alguno
    0.40
    Activations Density 0.128%

    No Known Activations