© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 245327
    Prev
    Next
    INDEX
    Explanations

    location and status updates

    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
     いく
    0.50
     berjumpa
    0.50
     wounded
    0.45
     これは
    0.45
     やっぱり
    0.45
     پیغمبر
    0.44
     wounding
    0.44
     銀
    0.44
     Roughly
    0.43
     特に
    0.43
    POSITIVE LOGITS
     doble
    0.45
     मील
    0.40
    0.40
    其他
    0.40
    Př
    0.40
    است
    0.38
    نيك
    0.38
     Oasis
    0.38
     performans
    0.38
     الهواء
    0.38
    Activations Density 0.000%

    No Known Activations