© 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. 172011
    Prev
    Next
    INDEX
    Explanations

    you copy

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

    punctuation and conjunctions

    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
    ڑ
    0.49
    ومی
    0.45
     rozwo
    0.45
     محیط
    0.44
    using
    0.43
    سی
    0.43
    Fly
    0.43
    ChooseServer
    0.42
     رأس
    0.42
     ingrédients
    0.42
    POSITIVE LOGITS
     లా
    0.49
     genuinely
    0.47
     zari
    0.47
     ahorita
    0.45
    跏
    0.44
     voorkomen
    0.44
    🇵
    0.43
    corso
    0.43
     hath
    0.43
    kons
    0.43
    Activations Density 0.001%

    No Known Activations