© 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. 2401
    Prev
    Next
    INDEX
    Explanations

    MRI and imaging scans

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

    MRI brain neuroimaging

    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
     ресторан
    0.55
     солдат
    0.55
    债务
    0.54
     Surety
    0.52
     диви
    0.52
     приви
    0.52
    묽
    0.52
     زع
    0.50
     Treasurer
    0.50
    诌
    0.50
    POSITIVE LOGITS
     imaging
    1.22
     MRI
    1.21
    MRI
    1.15
     voxel
    1.02
    imaging
    1.02
    成像
    0.95
     imaged
    0.90
    voxel
    0.90
     images
    0.89
     Imaging
    0.89
    Activations Density 0.045%

    No Known Activations