© 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. 48764
    Prev
    Next
    INDEX
    Explanations

    commercial use, production, real estate

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

    commercial success or compile

    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
    س
    1.15
    ας
    1.11
    ικ
    1.03
    ف
    1.03
    า
    1.02
    ır
    0.98
    ע
    0.98
    г
    0.96
    го
    0.95
    ли
    0.94
    POSITIVE LOGITS
    ۹
    1.23
     for
    1.09
    ről
    1.02
    {
    0.99
    at
    0.99
    >
    0.96
    تين
    0.94
    tat
    0.92
    dba
    0.92
     with
    0.92
    Activations Density 0.068%

    No Known Activations