© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 8294
    Prev
    Next
    INDEX
    Explanations

    geometry and manifolds

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

    spacetime curvature and warped shapes

    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_40_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ʦ
    0.42
    ⊆
    0.41
     finitely
    0.39
     EXECUTIVE
    0.39
     shuffled
    0.39
     stimulates
    0.37
     ರೆ
    0.37
     podcasts
    0.36
     probabilistic
    0.36
     ←
    0.36
    POSITIVE LOGITS
     curvature
    1.11
    curvature
    1.06
     curvatures
    1.00
     geodesic
    0.85
     submanifold
    0.82
     Riemannian
    0.80
     manifolds
    0.80
     manifold
    0.79
    manifolds
    0.78
     geodes
    0.77
    Activations Density 0.032%

    No Known Activations