© 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. 71076
    Prev
    Next
    INDEX
    Explanations

    foreign languages and specific terms

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

    open weights model

    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
    eg
    0.50
    intens
    0.48
     Increases
    0.47
    pros
    0.47
     ক্রমবর্ধমান
    0.46
    intra
    0.46
    forcement
    0.45
    prox
    0.44
    _{
    0.44
    Rx
    0.44
    POSITIVE LOGITS
     wybr
    0.55
     trochu
    0.51
     choisi
    0.50
     pranzo
    0.50
    เพราะ
    0.49
     dlatego
    0.47
     wymien
    0.47
     jego
    0.46
    知らない
    0.46
    เรื่อง
    0.46
    Activations Density 0.001%

    No Known Activations