© 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-16K
    7. 11377
    Prev
    Next
    INDEX
    Explanations

    dictionary and vocabulary

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

    synonyms and definitions

    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_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    瓏
    0.50
    订单
    0.49
     invitation
    0.48
     invitación
    0.48
    保険
    0.47
     procedimentos
    0.47
     requisitos
    0.45
     ইমরান
    0.45
    কমার্স
    0.45
     मोदी
    0.45
    POSITIVE LOGITS
     Dictionary
    1.34
     dictionary
    1.27
     dictionaries
    1.21
    Dictionary
    1.14
    dictionary
    1.14
    词
    1.07
     dicion
    1.05
     lexic
    1.04
    辞典
    1.04
    Dictionaries
    1.02
    Activations Density 0.158%

    No Known Activations