© 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. 75533
    Prev
    Next
    INDEX
    Explanations

    past participles and hence

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

    general / best scenarios requests

    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
     [#
    0.47
     റെ
    0.45
     momentary
    0.45
    玲
    0.45
     മറ്റ
    0.45
     Carolyn
    0.44
     }.
    0.44
     ።
    0.44
     Barbara
    0.43
     {%
    0.43
    POSITIVE LOGITS
    ض
    0.43
    ق
    0.43
    results
    0.43
    ဈ
    0.42
    FRS
    0.42
     lemah
    0.41
     narrowband
    0.41
    routeName
    0.40
    Islam
    0.40
    Attendees
    0.40
    Activations Density 0.001%

    No Known Activations