© 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. 235588
    Prev
    Next
    INDEX
    Explanations

    anterior cruciate, she got, only instroke

    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
    Number
    0.50
    InputField
    0.45
    dataTable
    0.45
     Catt
    0.44
    urii
    0.44
    OutputDir
    0.44
     Malk
    0.44
    Montana
    0.43
    _\
    0.43
    Selected
    0.43
    POSITIVE LOGITS
     kiz
    0.53
     khăn
    0.46
     handgun
    0.46
     গাঙ্গুলির
    0.45
     wrangler
    0.45
     cleansing
    0.45
     coupe
    0.44
     கிழக்கு
    0.44
    ᵗ
    0.44
     locking
    0.44
    Activations Density 0.000%

    No Known Activations