© 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. 111528
    Prev
    Next
    INDEX
    Explanations

    "if I," "our race," "end in," "the art"

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

    scientists trust

    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
    d
    0.54
    c
    0.54
    R
    0.53
     명
    0.52
    to
    0.52
    ID
    0.51
    J
    0.50
    Revolution
    0.50
    W
    0.50
    Method
    0.49
    POSITIVE LOGITS
    ならば
    0.49
     procéd
    0.48
     riguarda
    0.47
     decret
    0.47
     vittime
    0.47
     krijgen
    0.47
    贋
    0.47
     deur
    0.46
     tačiau
    0.46
    ึง
    0.46
    Activations Density 0.000%

    No Known Activations