© 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. 243272
    Prev
    Next
    INDEX
    Explanations

    closing estimate, hospital patients

    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
     কয়
    0.53
     Jeżeli
    0.47
    燔
    0.45
    预计
    0.44
     Kabel
    0.44
    投标
    0.44
     Eğer
    0.44
    记载
    0.44
     asegur
    0.43
    Zobacz
    0.43
    POSITIVE LOGITS
     ultimately
    0.47
     policies
    0.47
     not
    0.46
     laboratory
    0.44
     intestinal
    0.44
     sodium
    0.44
     final
    0.44
    ぬ
    0.44
     instrument
    0.43
     lep
    0.43
    Activations Density 0.001%

    No Known Activations