© 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. 184467
    Prev
    Next
    INDEX
    Explanations

    months and numbers

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

    instructions and context

    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
    困難
    0.48
     मुश्किल
    0.48
    rags
    0.47
     freezing
    0.46
    olc
    0.45
    艱
    0.45
     variational
    0.45
     draggable
    0.45
     Swinging
    0.44
    ័រ
    0.43
    POSITIVE LOGITS
    𒃶
    0.48
     باز
    0.48
     gennaio
    0.48
    iversary
    0.47
    mayı
    0.47
     সুন
    0.46
     xem
    0.45
     Arce
    0.45
    รู
    0.44
    May
    0.43
    Activations Density 0.002%

    No Known Activations