© 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-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-65K
    7. 3110
    Prev
    Next
    INDEX
    Explanations

    bill and debt payments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_29_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     திரி
    0.77
     przeb
    0.73
    Pseudo
    0.71
     증
    0.71
     pseudo
    0.71
     hermaph
    0.71
     ब्रो
    0.71
     પાર
    0.70
     Seals
    0.68
    점
    0.68
    POSITIVE LOGITS
     payments
    2.53
     payment
    2.46
    Payment
    2.33
    payment
    2.30
     Payment
    2.30
     Payments
    2.24
    Payments
    2.20
    payments
    2.17
     PAYMENT
    1.94
     paiement
    1.86
    Activations Density 0.295%

    No Known Activations