© 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. 40-GEMMASCOPE-2-RES-262K
    7. 3131
    Prev
    Next
    INDEX
    Explanations

    children's vocabulary

    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_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     now
    0.45
     clearly
    0.43
    лку
    0.42
     commercially
    0.42
     ribs
    0.41
    肋
    0.39
     firmly
    0.39
    aw
    0.38
     fault
    0.38
    얘
    0.37
    POSITIVE LOGITS
    naz
    0.51
     enfants
    0.50
     hráč
    0.47
     jogadores
    0.47
     çocuklar
    0.46
     uczniów
    0.46
    ⺠
    0.45
     Architektur
    0.45
     børn
    0.45
    ግራ
    0.44
    Activations Density 0.000%

    No Known Activations