© 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. 117792
    Prev
    Next
    INDEX
    Explanations

    data url prefixes

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

    data and date

    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
    ה
    0.47
    োগ্য
    0.45
    ্পর্শ
    0.43
    として
    0.43
    予約
    0.43
    лись
    0.42
    օ
    0.42
    н
    0.41
    ği
    0.41
     Libertad
    0.41
    POSITIVE LOGITS
     dort
    0.46
     concom
    0.46
     grafting
    0.44
     substit
    0.43
     textual
    0.43
     adverb
    0.43
     congru
    0.43
     deven
    0.43
     curbing
    0.42
     multimillion
    0.42
    Activations Density 0.002%

    No Known Activations