© 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
    3. Gemma-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 10334
    Prev
    Next
    INDEX
    Explanations

    words starting with pi

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

    Pi, pix, pixel, pill, pit, pivot

    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_40_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
    sth
    0.42
    yz
    0.39
     percept
    0.38
    sthe
    0.38
    fantastic
    0.38
    weiten
    0.38
    )']
    0.37
    viar
    0.37
    is
    0.36
    yto
    0.36
    POSITIVE LOGITS
     PI
    0.73
     пи
    0.73
     ピ
    0.73
     پی
    0.72
     пі
    0.71
     pi
    0.70
     Пі
    0.70
     Пи
    0.68
    Пи
    0.68
    ピ
    0.66
    Activations Density 0.186%

    No Known Activations