© 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. 92321
    Prev
    Next
    INDEX
    Explanations

    physical therapy, schematic failure

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

    conservation, persistent, array, boyfriend, blaming

    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
    btnInventory
    0.51
     সুর
    0.50
     প্রদর্শন
    0.50
     চিনি
    0.49
     Jokowi
    0.49
    Benzoimidazol
    0.47
     পণ
    0.47
     উপস্থাপন
    0.47
    湋
    0.47
     ø
    0.46
    POSITIVE LOGITS
     specialist
    0.48
     handsome
    0.48
     bookstore
    0.47
     requesting
    0.47
     receiver
    0.47
     market
    0.46
     schematic
    0.46
     practitioner
    0.46
     specialists
    0.46
     marketplace
    0.46
    Activations Density 0.000%

    No Known Activations