© 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. 177741
    Prev
    Next
    INDEX
    Explanations

    spheres, laboratories, microscopy, vessels

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

    energy, destruction, or conflict

    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
    我也
    0.48
     доля
    0.47
     також
    0.45
    retanto
    0.45
     usurp
    0.45
    昵
    0.45
    integrate
    0.43
    毀
    0.43
    啶
    0.43
     haberse
    0.43
    POSITIVE LOGITS
     that
    0.58
     microscopy
    0.54
     trays
    0.53
     areas
    0.52
     spheres
    0.51
     \[
    0.51
     surrounding
    0.50
     labs
    0.49
     laboratories
    0.49
     overlays
    0.49
    Activations Density 0.002%

    No Known Activations