© 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-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 48311
    Prev
    Next
    INDEX
    Explanations

    Who questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    y
    1.26
    t
    1.20
     as
    1.02
     are
    0.92
    s
    0.92
    k
    0.92
     to
    0.90
    r
    0.90
     at
    0.86
     who
    0.80
    POSITIVE LOGITS
    고
    1.04
     μπορεί
    0.87
    ation
    0.83
    in
    0.80
     (
    0.79
    :
    0.79
    ของ
    0.78
    라
    0.78
    เป็น
    0.75
    由
    0.75
    Activations Density 0.010%

    No Known Activations