© 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-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 49762
    Prev
    Next
    INDEX
    Explanations

    moles and hallmarks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    는
    0.63
    ির
    0.58
    on
    0.57
    Роз
    0.57
    Стро
    0.55
    🧱
    0.52
    จะ
    0.52
     بروز
    0.52
    ुरा
    0.52
    Housing
    0.52
    POSITIVE LOGITS
     uygulama
    0.59
     kı
    0.59
     sın
    0.58
     yeti
    0.58
    󠁿
    0.58
    atasaray
    0.56
     становника
    0.55
    一張
    0.55
     yaşam
    0.55
    antwoord
    0.54
    Activations Density 0.003%

    No Known Activations