© 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. 155628
    Prev
    Next
    INDEX
    Explanations

    nature Buddhism study

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

    in phrases ending in punctuation

    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
     mantenere
    0.52
     pernikahan
    0.49
     Simeon
    0.49
     incluida
    0.48
    婼
    0.47
     disert
    0.46
    戬
    0.46
    洺
    0.46
     syukur
    0.46
     tumbuhan
    0.46
    POSITIVE LOGITS
    on
    0.58
    is
    0.54
    in
    0.52
    front
    0.50
    FRONT
    0.48
    are
    0.48
    ro
    0.47
    ul
    0.47
    orbital
    0.47
    for
    0.46
    Activations Density 0.001%

    No Known Activations