© 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. 176965
    Prev
    Next
    INDEX
    Explanations

    readings indicate

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

    burning smells

    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
     فوجی
    0.49
    軍
    0.46
    宣布
    0.45
    政治
    0.45
    說是
    0.44
     軍
    0.44
    訲
    0.44
     দিকে
    0.44
    守
    0.44
     পুন
    0.43
    POSITIVE LOGITS
     editable
    0.49
    Cafe
    0.45
     füh
    0.45
    ProgressBar
    0.45
     Artificial
    0.44
     você
    0.43
     Вам
    0.43
     unopened
    0.43
    Рабо
    0.42
     Jugendlichen
    0.42
    Activations Density 0.003%

    No Known Activations