© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 165193
    Prev
    Next
    INDEX
    Explanations

    specific nouns and phrases

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

    claim legitimate owners redress file

    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
    Not in Any Lists

    No Comments

    Negative Logits
     inconven
    0.51
    実
    0.48
    桌
    0.47
    creation
    0.46
    ირო
    0.46
    dinner
    0.45
    pesas
    0.45
    tray
    0.44
    ضی
    0.44
    τικών
    0.44
    POSITIVE LOGITS
     H
    0.52
     Huy
    0.46
     descendants
    0.45
     Hyg
    0.45
     Glastonbury
    0.44
     Mountaine
    0.43
    एचओ
    0.43
     then
    0.43
     WARNING
    0.43
     ARMY
    0.43
    Activations Density 0.000%

    No Known Activations