© 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. 149192
    Prev
    Next
    INDEX
    Explanations

    payment or financial terms

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

    certifications, payments, transfers

    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
    ulte
    0.48
    їв
    0.47
    Dengan
    0.46
    ╧
    0.45
    Probably
    0.45
    jupiter
    0.45
    Contin
    0.44
     sitten
    0.43
    叫
    0.43
    Diagn
    0.42
    POSITIVE LOGITS
     indemn
    0.53
     payments
    0.50
     maneuvers
    0.49
     establishments
    0.47
     payment
    0.46
     certifications
    0.46
     Payment
    0.44
    payment
    0.43
     Payments
    0.43
     dinners
    0.43
    Activations Density 0.000%

    No Known Activations