© 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. 29351
    Prev
    Next
    INDEX
    Explanations

    China was/is

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

    secrets and conspiracies

    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
     турни
    0.52
    ᶤ
    0.50
    हु
    0.49
     môi
    0.49
    περι
    0.49
     тэ
    0.48
    ল
    0.48
    ໃ
    0.48
    т
    0.47
    ל
    0.47
    POSITIVE LOGITS
     Physics
    0.43
     फिजिक्स
    0.43
     redness
    0.43
     Geheim
    0.43
    ref
    0.41
     frictionless
    0.40
    ysel
    0.40
     communism
    0.39
    hmann
    0.39
     Physik
    0.39
    Activations Density 0.000%

    No Known Activations