© 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. 199032
    Prev
    Next
    INDEX
    Explanations

    dual screening

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

    power and harm

    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
     წლის
    0.56
    پن
    0.55
    وس
    0.51
    ق
    0.50
    زي
    0.50
     Medien
    0.49
    Estas
    0.48
    ის
    0.48
    Estos
    0.48
     იაპ
    0.47
    POSITIVE LOGITS
    ate
    0.62
    ite
    0.61
    -
    0.54
    iter
    0.54
    att
    0.52
    ile
    0.50
     Section
    0.50
    ico
    0.50
    eness
    0.49
    est
    0.48
    Activations Density 0.000%

    No Known Activations