© 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. 228366
    Prev
    Next
    INDEX
    Explanations

    conference and section

    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
    เมื่อ
    0.66
    ル
    0.61
    Когда
    0.60
    Quando
    0.57
    quando
    0.54
    Cuando
    0.53
    מ
    0.53
    cuando
    0.53
    importanza
    0.52
    ザ
    0.52
    POSITIVE LOGITS
     đặt
    0.53
     milli
    0.50
     of
    0.49
     by
    0.47
     Chiropractic
    0.46
     führt
    0.46
     официально
    0.45
     embarking
    0.45
     Millennials
    0.45
     öffentlich
    0.45
    Activations Density 0.000%

    No Known Activations