© 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. 172002
    Prev
    Next
    INDEX
    Explanations

    alternative provision and quantities

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

    most recent

    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
    ADE
    0.45
     marinade
    0.45
     مال
    0.44
     الي
    0.44
     الحس
    0.44
     دون
    0.44
     JA
    0.44
     delusion
    0.44
     s
    0.43
    老師
    0.43
    POSITIVE LOGITS
    έχ
    0.51
     bebê
    0.50
    ান
    0.48
     bezpośred
    0.48
    ্রেট
    0.46
     vrlo
    0.45
     particolari
    0.45
    のひとつ
    0.44
     coeffs
    0.44
    ब्दी
    0.44
    Activations Density 0.000%

    No Known Activations