© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 127637
    Prev
    Next
    INDEX
    Explanations

    international words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    が
    -1.30
    と
    -1.30
     basically
    -1.21
     get
    -1.20
     probably
    -1.16
     seem
    -1.16
    इट
    -1.15
    ■
    -1.13
     что
    -1.11
     also
    -1.09
    POSITIVE LOGITS
     Spanyol
    1.13
    bedien
    1.13
    aqui
    1.08
    telep
    1.00
    geladen
    0.99
    めで
    0.98
     Banken
    0.98
    を描く
    0.98
     confound
    0.98
     Phòng
    0.96
    Activations Density 0.504%

    No Known Activations