© 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. 226706
    Prev
    Next
    INDEX
    Explanations

    location, status, or transition

    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
    碰撞
    0.54
     характеристики
    0.48
    哃
    0.46
     özellikleri
    0.46
     MONEY
    0.45
     COURSE
    0.43
    驾
    0.42
    晦
    0.42
    цент
    0.42
     Chủ
    0.41
    POSITIVE LOGITS
    ክር
    0.45
     phage
    0.45
    SVM
    0.45
     occupation
    0.45
     damped
    0.44
     lodges
    0.44
     रुग्ण
    0.43
     observación
    0.43
     neutrino
    0.43
    atanga
    0.43
    Activations Density 0.000%

    No Known Activations