© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-270M
    3. 15-GEMMASCOPE-2-RES-16K
    4. 4787
    Prev
    Next
    INDEX
    Explanations

    conjunction and

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_15_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
     alike
    2.71
    냐면
    2.64
     sebagainya
    2.63
    }}]{
    2.62
    dDays
    2.62
     같다
    2.58
     비슷
    2.57
    <unused998>
    2.49
     ไหร่
    2.49
    Pkg
    2.49
    POSITIVE LOGITS
     and
    10.95
     và
    9.06
    and
    8.81
    และ
    8.68
     и
    7.72
    および
    7.70
     AND
    7.69
     dan
    7.57
    及び
    7.50
     &
    7.47
    Activations Density 20.649%

    No Known Activations