© 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. 181480
    Prev
    Next
    INDEX
    Explanations

    stretched limousines, unlike motorcycles

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

    Coronary Artery Disease (CAD)

    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
    닿
    0.48
     RtlOverlay
    0.47
    <unused90>
    0.47
     fortitude
    0.47
     antiguas
    0.47
     kucing
    0.46
     Celtic
    0.46
     kèo
    0.46
     centroid
    0.45
     buenas
    0.45
    POSITIVE LOGITS
    You
    0.48
    Causes
    0.47
    Designed
    0.45
    criptive
    0.43
    Eisen
    0.41
    わかり
    0.41
    🚍
    0.41
     Causes
    0.40
     pauses
    0.40
    Materials
    0.40
    Activations Density 0.000%

    No Known Activations