© 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. 246715
    Prev
    Next
    INDEX
    Explanations

    gentle assumption

    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
     Làm
    0.50
     Archaeological
    0.49
    );"
    0.49
     Archaeology
    0.47
     Ghosts
    0.47
     Possession
    0.46
    ScrollView
    0.46
     Prints
    0.46
     Restore
    0.46
     Induction
    0.46
    POSITIVE LOGITS
    uli
    0.49
    ateful
    0.48
     sy
    0.48
    heng
    0.47
     revue
    0.47
    ۔
    0.47
    aub
    0.47
    ole
    0.46
    uta
    0.46
     ਜਾਣ
    0.46
    Activations Density 0.000%

    No Known Activations