© 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. 235429
    Prev
    Next
    INDEX
    Explanations

    UN recognition, different city

    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
     riferimento
    0.55
    ርዝ
    0.54
    걱
    0.54
     упраж
    0.50
    포츠
    0.49
     দুর্ভোগ
    0.49
     एक्सरसाइज
    0.49
    सरकारी
    0.49
     보험
    0.48
    綀
    0.48
    POSITIVE LOGITS
    elephant
    0.42
    u
    0.41
    extension
    0.40
     BUILD
    0.40
    aro
    0.40
    feb
    0.39
    knit
    0.39
    jenis
    0.38
    hydraz
    0.37
    ethe
    0.37
    Activations Density 0.002%

    No Known Activations