© 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. 199116
    Prev
    Next
    INDEX
    Explanations

    Bulgaria, weddings, host family

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

    quality of data, context

    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
    uer
    0.50
     коронави
    0.49
    abies
    0.49
    oue
    0.48
    ʉ
    0.48
    itz
    0.48
    ujeme
    0.48
    ographies
    0.47
    ression
    0.47
    oczy
    0.46
    POSITIVE LOGITS
     Regis
    0.48
    слав
    0.47
    V
    0.44
    껀
    0.44
     Jahn
    0.42
    blacklist
    0.41
    다
    0.41
     쓰
    0.40
     Ayl
    0.40
    Da
    0.40
    Activations Density 0.000%

    No Known Activations