© 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. 199015
    Prev
    Next
    INDEX
    Explanations

    view George's tribute page

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

    coloring book

    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
    otic
    0.49
    ry
    0.48
    atan
    0.48
    omas
    0.47
    ator
    0.47
    imer
    0.47
    !"
    0.46
     숨
    0.46
    imas
    0.46
    ies
    0.45
    POSITIVE LOGITS
     Superintend
    0.51
     tuition
    0.46
     elucidate
    0.46
     takeaways
    0.46
     allowNull
    0.46
     নাব
    0.45
    ాతీయ
    0.44
    ిత
    0.44
    েনার
    0.44
     publicação
    0.44
    Activations Density 0.000%

    No Known Activations