© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 1267
    Prev
    Next
    INDEX
    Explanations

    MRI, brain imaging, or technical contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    στή
    -0.93
     concave
    -0.90
     logarithmic
    -0.81
     pancre
    -0.79
     atto
    -0.79
    ilova
    -0.77
    ERIA
    -0.77
     Mandi
    -0.75
     детский
    -0.75
     venison
    -0.75
    POSITIVE LOGITS
     radiological
    0.87
     imaging
    0.82
    MRI
    0.81
     przet
    0.78
     MR
    0.77
     voxel
    0.75
    tract
    0.70
     kebenaran
    0.69
     MRI
    0.68
     brain
    0.68
    Activations Density 0.043%

    No Known Activations