© 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. 206118
    Prev
    Next
    INDEX
    Explanations

    international, geopolitical, or cultural topics

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

    arithmetic operators and programming commands

    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
     ሂደት
    0.57
    ﺖ
    0.55
    ują
    0.51
    oil
    0.50
    ută
    0.50
     эпоху
    0.50
    є
    0.50
    기에
    0.49
    ape
    0.49
    ệc
    0.49
    POSITIVE LOGITS
     konst
    0.47
     Kurds
    0.45
    صفوف
    0.43
    ज
    0.43
     consulate
    0.43
     supermarkets
    0.43
     dist
    0.43
     konflik
    0.43
     kons
    0.42
     const
    0.42
    Activations Density 0.000%

    No Known Activations