© 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. 219749
    Prev
    Next
    INDEX
    Explanations

    risk well, payment card, trading system

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

    payments and foreign words

    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
     Beds
    0.50
    duğu
    0.46
     Periods
    0.44
    ্তিক
    0.44
     Chow
    0.43
    듬
    0.43
    يد
    0.42
    ße
    0.42
     Cuisine
    0.42
     वड
    0.41
    POSITIVE LOGITS
    s
    0.49
     levy
    0.47
     hoofd
    0.47
    рьох
    0.46
     myriad
    0.46
     lebar
    0.46
     pyramidal
    0.46
     zdrav
    0.46
     bandwagon
    0.46
     shrugged
    0.45
    Activations Density 0.000%

    No Known Activations