© 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. 74123
    Prev
    Next
    INDEX
    Explanations

    words starting with p

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

    peace Prize

    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
    a
    1.15
    i
    0.87
    and
    0.82
    an
    0.77
    as
    0.76
    e
    0.76
    be
    0.75
    ;
    0.75
    the
    0.74
    ac
    0.73
    POSITIVE LOGITS
    ุ
    0.76
    大
    0.75
     aeruginosa
    0.75
    ляется
    0.73
    了他的
    0.73
     p
    0.72
    ↵↵
    0.72
    у
    0.71
    ул
    0.70
    คุณ
    0.70
    Activations Density 1.957%

    No Known Activations