© 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. 211896
    Prev
    Next
    INDEX
    Explanations

    itself from

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

    Cross-language concepts and technical terms

    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
     操作
    0.51
     完全
    0.48
     四
    0.47
     所有
    0.47
     你
    0.45
     令
    0.44
    img
    0.43
    DISABLE
    0.43
     あなた
    0.43
    ="">
    0.42
    POSITIVE LOGITS
     Germ
    0.47
    Construct
    0.46
     Modell
    0.46
     клас
    0.46
     трубо
    0.45
     allemande
    0.45
     انگل
    0.45
     Construct
    0.42
     museums
    0.42
    ટું
    0.42
    Activations Density 0.001%

    No Known Activations