© 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. 16-GEMMASCOPE-2-RES-16K
    7. 628
    Prev
    Next
    INDEX
    Explanations

    foreign language terms

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

    foreign words, numbers, numbers followed by periods

    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_16_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     Unicode
    0.50
    8
    0.48
    但在
    0.46
     YOLO
    0.46
    9
    0.45
     unicode
    0.44
     chloroplast
    0.43
    from
    0.43
    1
    0.42
     Solidity
    0.41
    POSITIVE LOGITS
     wieder
    0.46
     monsieur
    0.46
     musste
    0.45
     avrebbe
    0.45
     kellett
    0.44
     petición
    0.43
     aveva
    0.43
     avaient
    0.43
     weer
    0.42
     levando
    0.42
    Activations Density 0.021%

    No Known Activations