© 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. 80993
    Prev
    Next
    INDEX
    Explanations

    credit, credit card, credit line

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

    credit, credit checks, credit applications

    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
    '
    0.80
    ।
    0.78
    !
    0.77
    ion
    0.75
    ’
    0.73
    0.71
    。
    0.68
    ้
    0.66
    ли
    0.64
    ся
    0.61
    POSITIVE LOGITS
     crédito
    0.96
    CRED
    0.95
     credit
    0.94
    Credit
    0.92
     креди
    0.86
     Credit
    0.85
     credits
    0.85
    Credits
    0.85
     kred
    0.85
     credito
    0.84
    Activations Density 0.039%

    No Known Activations