© 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. 93
    Prev
    Next
    INDEX
    Explanations

    blood clot, clotting, thrombosis

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

    blood clots and clotting

    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
    美术
    0.53
     बेरोजगारी
    0.52
    晠
    0.51
     ครู
    0.51
    懑
    0.50
    沔
    0.49
     కళ
    0.49
    केमॉन
    0.49
    乐
    0.49
     শিল্পী
    0.48
    POSITIVE LOGITS
     anticoagulant
    1.25
     anticoag
    1.22
     thromb
    1.19
     fibrin
    1.19
     thrombosis
    1.11
     clotting
    1.11
     throm
    1.10
     platelets
    1.06
     platelet
    1.04
     coagulation
    1.04
    Activations Density 0.042%

    No Known Activations