© 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. 166680
    Prev
    Next
    INDEX
    Explanations

    create book

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

    searching through text

    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
     pleasant
    0.47
     Smyrna
    0.47
    颞
    0.47
     euh
    0.46
     Metcalf
    0.46
     glorie
    0.46
    quisite
    0.46
    ijski
    0.46
     مطلوب
    0.45
    快適
    0.45
    POSITIVE LOGITS
    STEP
    0.52
    BOOK
    0.52
    ATE
    0.51
    COLORS
    0.50
    ATIVE
    0.48
    GLASS
    0.48
    𝘀
    0.48
    CHAPTER
    0.48
    IONS
    0.47
    NOTES
    0.47
    Activations Density 0.000%

    No Known Activations