© 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. 77972
    Prev
    Next
    INDEX
    Explanations

    rights and modifications

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

    foreign words and concepts

    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
     waxaa
    0.52
     crónica
    0.44
     बनाये
    0.43
     miraculously
    0.43
    潇
    0.43
    имуще
    0.42
    映像
    0.42
    无比
    0.41
     appBar
    0.41
     inconclusive
    0.41
    POSITIVE LOGITS
     killers
    0.39
     समझते
    0.38
     trafic
    0.38
     strangers
    0.38
     öğretmen
    0.38
     শ্রমিক
    0.38
     elektromagnet
    0.38
     laborers
    0.37
    ishing
    0.37
    ឺ
    0.37
    Activations Density 0.002%

    No Known Activations