© 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. 153028
    Prev
    Next
    INDEX
    Explanations

    rectangles represent

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

    exceptional capabilities

    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
     वो
    0.46
    Head
    0.44
     Single
    0.44
    keletal
    0.43
    ูก
    0.42
     Head
    0.41
    Improving
    0.41
    *
    0.41
    Smaller
    0.40
    гот
    0.40
    POSITIVE LOGITS
     devoir
    0.57
    ępuje
    0.51
     သိ
    0.51
     bigli
    0.49
     wellknown
    0.49
     giãn
    0.48
     avrà
    0.48
     приве
    0.47
     দূরে
    0.47
     mettere
    0.47
    Activations Density 0.001%

    No Known Activations