© 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-262K
    7. 149902
    Prev
    Next
    INDEX
    Explanations

    words following punctuation or specific nouns

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

    identifies negation and contrast

    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
    Negative Logits
    edy
    0.53
    ubert
    0.45
    affin
    0.45
    inser
    0.44
    писи
    0.43
    affer
    0.43
    aque
    0.42
     Tafel
    0.41
    umam
    0.41
    à
    0.41
    POSITIVE LOGITS
     thôi
    0.48
     desn
    0.47
     alone
    0.46
    !='
    0.46
     yalnız
    0.45
     đừng
    0.45
     zewnętr
    0.44
     trei
    0.44
     ثلاثة
    0.44
     هیچ
    0.43
    Activations Density 0.001%

    No Known Activations