© 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. 102720
    Prev
    Next
    INDEX
    Explanations

    foreign or specialized words

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

    foreign words or phrases

    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
    Not in Any Lists

    No Comments

    Negative Logits
     B
    0.52
     bib
    0.52
     A
    0.50
     discovered
    0.48
    ag
    0.48
     k
    0.48
    ai
    0.48
     device
    0.47
    :
    0.47
     detected
    0.46
    POSITIVE LOGITS
     иностран
    0.51
     भविष्य
    0.51
    Ꮠ
    0.50
    व्यों
    0.49
     పోటీ
    0.48
    牒
    0.47
     raping
    0.46
    규모
    0.45
     bicovariant
    0.45
    ру
    0.44
    Activations Density 0.001%

    No Known Activations