© 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. 200054
    Prev
    Next
    INDEX
    Explanations

    bancario or banking concepts

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

    cooga

    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
     basse
    0.50
     segment
    0.47
     basi
    0.46
    公司
    0.44
    ص
    0.44
    ึ่ง
    0.43
    山市
    0.42
    说说
    0.42
    ings
    0.42
     Boston
    0.41
    POSITIVE LOGITS
     დიდ
    0.54
    н
    0.53
    ISE
    0.51
    NU
    0.49
    OVA
    0.48
    лм
    0.46
    ЕН
    0.46
    НА
    0.46
    ాలే
    0.46
    вы
    0.45
    Activations Density 0.002%

    No Known Activations