© 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. 16-GEMMASCOPE-2-RES-16K
    7. 406
    Prev
    Next
    INDEX
    Explanations

    people and family names

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

    quarter mile or pounder

    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_16_width_16k_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
    an
    0.80
    as
    0.80
    to
    0.77
    t
    0.74
    p
    0.70
    ad
    0.67
    the
    0.65
    l
    0.65
    for
    0.63
    up
    0.63
    POSITIVE LOGITS
     strikingly
    0.67
     受け
    0.64
     aides
    0.62
    ద్రా
    0.62
     scolded
    0.62
     swearing
    0.61
     fáciles
    0.61
     baseless
    0.61
    ishing
    0.60
     unmarried
    0.60
    Activations Density 0.000%

    No Known Activations