© 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. 249976
    Prev
    Next
    INDEX
    Explanations

    foreign language 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
    梗
    0.48
     morales
    0.44
    ە
    0.42
    तालों
    0.41
    푯
    0.41
    ңы
    0.40
     பாட
    0.40
    ‼️
    0.39
     forgets
    0.39
    غ
    0.39
    POSITIVE LOGITS
     디지털
    0.48
    ousing
    0.43
     הר
    0.41
     Mitsubishi
    0.40
     பிற
    0.39
    Cinema
    0.39
     unveiling
    0.39
     הד
    0.39
     మరింత
    0.39
     weitere
    0.39
    Activations Density 0.001%

    No Known Activations