© 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. 156574
    Prev
    Next
    INDEX
    Explanations

    cross-lingual vocabulary

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

    instruction, advice, definition

    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
    exhaustive
    0.53
    문에
    0.49
    agents
    0.46
    in
    0.46
    이
    0.46
    factorial
    0.46
    solution
    0.45
    inclusion
    0.45
    Solution
    0.44
    Liv
    0.44
    POSITIVE LOGITS
     そして
    0.51
     crap
    0.50
     моего
    0.50
     whatnot
    0.49
     আইডিয়া
    0.48
     नकारात्मक
    0.48
     こんな
    0.48
     Nullam
    0.47
     клуба
    0.47
    ן
    0.47
    Activations Density 0.001%

    No Known Activations