© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 143643
    Prev
    Next
    INDEX
    Explanations

    place names and titles

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

    duplicate key

    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
    `}
    0.53
    ```{
    0.52
    ()`
    0.51
     গুঁ
    0.49
    tFileInputExcel
    0.49
    )+"]
    0.49
    ຝ
    0.48
    钨
    0.47
     குழ
    0.47
    𒍑
    0.47
    POSITIVE LOGITS
     Lowell
    0.51
     Louisiana
    0.47
     President
    0.45
     (
    0.44
    Rose
    0.44
    :
    0.44
     Baron
    0.44
     Rose
    0.43
     rah
    0.42
     Interstate
    0.42
    Activations Density 0.002%

    No Known Activations