© 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. 139946
    Prev
    Next
    INDEX
    Explanations

    higher air

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

    languages and specific topics

    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
    填
    0.47
     scoperto
    0.45
     enggak
    0.44
     soltanto
    0.43
     elektromagnet
    0.43
     questa
    0.42
     conoscenze
    0.42
     cea
    0.41
     titulares
    0.41
    خصص
    0.41
    POSITIVE LOGITS
     MRP
    0.56
    anomaly
    0.55
     ド
    0.55
     アルミ
    0.55
     Дэ
    0.54
     関係
    0.54
     मुआवजा
    0.53
    gings
    0.52
     अहं
    0.52
     アク
    0.51
    Activations Density 0.000%

    No Known Activations