© 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. 108045
    Prev
    Next
    INDEX
    Explanations

    language identification

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

    demand

    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
     φυ
    0.54
    tains
    0.48
    зира
    0.45
    र्य
    0.45
    quered
    0.44
     phospholipid
    0.43
    بینی
    0.43
    ):
    0.43
     runoff
    0.43
     ADP
    0.43
    POSITIVE LOGITS
    Forms
    0.52
    bilisi
    0.49
    Seriously
    0.46
    Michele
    0.46
    সির
    0.43
     ويب
    0.43
     čo
    0.43
     počet
    0.42
    選択
    0.42
     লিস্ট
    0.42
    Activations Density 0.000%

    No Known Activations