© 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. 192066
    Prev
    Next
    INDEX
    Explanations

    weekend indeed

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

    tests aim, Key events

    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
    นี่
    0.57
    ки
    0.52
    น
    0.51
    Prima
    0.51
    Hel
    0.47
    บริเวณ
    0.47
     чувство
    0.46
    є
    0.46
     Prima
    0.45
     prima
    0.44
    POSITIVE LOGITS
     refinements
    0.57
     subsets
    0.55
     pushes
    0.52
     posits
    0.52
     assemblies
    0.50
     toroidal
    0.50
     antisymmetric
    0.49
     confronts
    0.49
     bosonic
    0.49
     existentes
    0.48
    Activations Density 0.000%

    No Known Activations