© 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. 159850
    Prev
    Next
    INDEX
    Explanations

    list items and actions

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

    list items or structured text

    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
    ير
    0.55
     disruptive
    0.52
    家の
    0.52
    ンド
    0.51
    ΙΚ
    0.51
    ラ
    0.49
    лад
    0.49
    ЛА
    0.48
    milk
    0.48
    スター
    0.48
    POSITIVE LOGITS
     Weights
    0.54
    ahari
    0.51
     azal
    0.50
     അതേ
    0.49
     Significance
    0.48
     ć
    0.46
     अलविदा
    0.44
     Bedeutung
    0.44
     स्पर्धा
    0.43
     Resources
    0.43
    Activations Density 0.000%

    No Known Activations