© 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. 56582
    Prev
    Next
    INDEX
    Explanations

    the top is or arc

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

    values, context, or options

    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
     प्रारंभिक
    0.57
     ჰ
    0.52
    斟
    0.52
     પ
    0.52
     ერთ
    0.49
    resión
    0.48
     հ
    0.48
    larına
    0.48
     автомо
    0.47
     συν
    0.47
    POSITIVE LOGITS
    >(&
    0.47
    >';
    0.47
    ਸੀਂ
    0.44
    ائد
    0.44
     cancers
    0.43
    ശ്ശ
    0.43
    وبات
    0.42
    会将
    0.42
    PhD
    0.42
     Exception
    0.41
    Activations Density 0.000%

    No Known Activations