© 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. 56478
    Prev
    Next
    INDEX
    Explanations

    multilingual descriptions of features or content

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

    religious texts and plural possessives

    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
     alanı
    0.49
     pourra
    0.42
    ப்பான்
    0.41
     нього
    0.41
    یشہ
    0.40
    zyme
    0.40
    зыка
    0.39
    拧
    0.39
     βρίσκεται
    0.38
    綎
    0.38
    POSITIVE LOGITS
    their
    0.40
     warriors
    0.39
    ަނ
    0.39
     সেগুলো
    0.38
    Tenemos
    0.38
    マー
    0.38
     বট
    0.37
    न्द्रीय
    0.37
    螻
    0.37
    它们的
    0.36
    Activations Density 0.033%

    No Known Activations