© 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. 85753
    Prev
    Next
    INDEX
    Explanations

    latex date command

    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
     tassels
    0.42
    상
    0.42
    PCs
    0.41
     tradicional
    0.41
    #(
    0.40
    ㈱
    0.40
    ㈜
    0.39
     tradicionales
    0.39
    τε
    0.39
     COMPANY
    0.38
    POSITIVE LOGITS
    ləş
    0.45
     Zor
    0.44
    iatan
    0.44
    动
    0.43
     розпо
    0.42
    硕
    0.42
     аст
    0.41
     प्रोटीन
    0.41
     лечение
    0.41
     Tumor
    0.41
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.