© 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. 135201
    Prev
    Next
    INDEX
    Explanations

    our US and Canadian tax issues

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

    fill in the blanks

    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
    ط
    0.54
    ת
    0.49
    ↵↵
    0.48
    toare
    0.45
    </u>
    0.44
    tableau
    0.44
    ער
    0.43
    -
    0.43
    תו
    0.42
    </em>
    0.42
    POSITIVE LOGITS
     เงี้ย
    0.54
     ナイス
    0.52
     置
    0.51
     やす
    0.51
     可愛い
    0.51
    ্ী
    0.50
    MQ
    0.50
    CCOCC
    0.49
    飾り
    0.49
     Xuân
    0.49
    Activations Density 0.000%

    No Known Activations