© 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. 228297
    Prev
    Next
    INDEX
    Explanations

    high blood pressure or diabetes

    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
    umls
    0.51
    （
    0.47
    icch
    0.46
    rins
    0.45
    。「
    0.45
    elev
    0.45
    妙
    0.44
    washer
    0.44
     जानें
    0.44
    む
    0.44
    POSITIVE LOGITS
    <>();
    0.54
    ClassName
    0.49
    ௫
    0.47
    ]}.
    0.47
    لاک
    0.46
    GoString
    0.46
    QSizePolicy
    0.46
    യായി
    0.44
    ][]
    0.43
    -;
    0.43
    Activations Density 0.005%

    No Known Activations