© 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. 127497
    Prev
    Next
    INDEX
    Explanations

    speed time

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

    warnings and disclaimers

    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
     Сайт
    0.50
     Surgery
    0.49
    巉
    0.49
     Cancer
    0.48
     boek
    0.46
     trenches
    0.46
    䡊
    0.45
     Brewery
    0.45
     immobil
    0.44
    strdup
    0.44
    POSITIVE LOGITS
     тебя
    0.46
    睦
    0.46
     является
    0.45
     ADJUST
    0.43
    猊
    0.43
     MAH
    0.43
     inclui
    0.43
     whaka
    0.42
    ạt
    0.42
     вмеша
    0.42
    Activations Density 0.000%

    No Known Activations