© 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. 192560
    Prev
    Next
    INDEX
    Explanations

    France played

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

    practice explaining quality

    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
     pharmacy
    0.47
     scanty
    0.46
     cupcake
    0.46
     lemonade
    0.45
     meagre
    0.45
    ྩ
    0.44
     profitable
    0.44
     cookware
    0.43
     speedy
    0.43
     apothecary
    0.42
    POSITIVE LOGITS
    的一些
    0.55
     Nonetheless
    0.50
    OLOGICAL
    0.46
     일부
    0.45
    癹
    0.45
    砷
    0.45
    㧍
    0.44
     Statewide
    0.44
    OLDER
    0.43
     البعض
    0.43
    Activations Density 0.001%

    No Known Activations