© 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. 260425
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    wał
    0.51
    others
    0.50
    nitř
    0.50
    مرة
    0.48
    Does
    0.48
    érieur
    0.48
    tom
    0.47
    🏈
    0.47
    czyć
    0.47
     อื่น
    0.47
    POSITIVE LOGITS
     inhomogeneous
    0.52
     cosmology
    0.52
     gravity
    0.50
     elastic
    0.49
     diffraction
    0.49
     chiral
    0.48
     calculation
    0.48
     resistivity
    0.48
     alpine
    0.48
     larch
    0.48
    Activations Density 0.002%

    No Known Activations