© 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. 65832
    Prev
    Next
    INDEX
    Explanations

    loss, areas, broker, automatically, remain

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

    surplus, spots, should, corresponding

    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
     lymphocyte
    0.51
     температура
    0.50
    淨
    0.49
     bếp
    0.49
     barefoot
    0.48
    。...
    0.47
     lymphoma
    0.46
     precaution
    0.46
     。
    0.46
     yemek
    0.45
    POSITIVE LOGITS
     Tecn
    0.54
    bourg
    0.52
     Techn
    0.48
    आन
    0.48
    eurs
    0.47
     Quelles
    0.47
     Technische
    0.46
    jarige
    0.46
     इश
    0.46
     Imran
    0.46
    Activations Density 0.002%

    No Known Activations