© 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. 176480
    Prev
    Next
    INDEX
    Explanations

    unexpected/foreign words

    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
     일반적으로
    0.44
     如
    0.43
     όπως
    0.41
    依照
    0.41
     基于
    0.41
     CODE
    0.40
     기반
    0.39
    按
    0.39
     termos
    0.39
     Enlight
    0.39
    POSITIVE LOGITS
    били
    0.45
    늦
    0.42
    ung
    0.41
    
    0.41
     ostrich
    0.40
    obao
    0.39
     roi
    0.39
     ojo
    0.39
    कृष्ट
    0.39
     ple
    0.38
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.