© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 158005
    Prev
    Next
    INDEX
    Explanations

    regular antiplatelet therapy

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

    taking factors into account

    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
    Not in Any Lists

    No Comments

    Negative Logits
    AcOH
    0.58
     ASSOCI
    0.57
     alcohols
    0.56
    槙
    0.55
     AcOH
    0.54
     OWNER
    0.54
     finland
    0.54
    НА
    0.53
    ONOM
    0.52
     hton
    0.52
    POSITIVE LOGITS
    žno
    0.50
    verting
    0.49
    works
    0.48
     Bog
    0.46
    pping
    0.46
    :
    0.46
    ingt
    0.46
    uster
    0.45
    jection
    0.45
    ppy
    0.45
    Activations Density 0.001%

    No Known Activations