© 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. 132119
    Prev
    Next
    INDEX
    Explanations

    professionals who are real

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

    suggesting content

    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
    Not in Any Lists

    No Comments

    Negative Logits
    갚
    0.41
     manufactured
    0.41
     fråga
    0.41
     contradiction
    0.40
    ەی
    0.40
     sensit
    0.39
    を有する
    0.38
    桷
    0.38
    երը
    0.38
     fabricated
    0.38
    POSITIVE LOGITS
    our
    0.61
    italian
    0.54
     приятно
    0.54
     מק
    0.52
     أصبح
    0.52
     Кли
    0.51
     רו
    0.50
    thirty
    0.49
    alé
    0.49
    ئة
    0.49
    Activations Density 0.000%

    No Known Activations