© 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. 123671
    Prev
    Next
    INDEX
    Explanations

    your wedding

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

    instead of vague terms

    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
     βρί
    0.45
    这一
    0.43
     indépend
    0.43
    তিন
    0.42
     ajustable
    0.41
    铜
    0.41
     takže
    0.41
    痪
    0.40
    тона
    0.40
     indexing
    0.40
    POSITIVE LOGITS
    imagens
    0.50
    ik
    0.48
     Rwand
    0.47
    immagine
    0.47
    ู่
    0.44
    די
    0.43
    ImageUrl
    0.43
    fromParams
    0.42
    ixin
    0.42
     Kies
    0.42
    Activations Density 0.001%

    No Known Activations