© 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. 18246
    Prev
    Next
    INDEX
    Explanations

    official Korean phrases

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

    sequences of numbers and letter combinations

    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
    ת
    1.19
    us
    1.02
    ت
    0.94
    n
    0.93
    ക
    0.89
    ע
    0.86
    ن
    0.83
    न
    0.82
    t
    0.82
    س
    0.82
    POSITIVE LOGITS
    2
    1.09
    {
    1.05
    3
    1.05
    ffic
    0.99
     불구하고
    0.95
    <0x80>
    0.91
     인해
    0.89
    '
    0.87
     인한
    0.84
    fficial
    0.83
    Activations Density 0.370%

    No Known Activations