© 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. 22-GEMMASCOPE-2-RES-65K
    7. 8043
    Prev
    Next
    INDEX
    Explanations

    payday loans and cash advance

    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_22_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
    和服务
    0.84
     aspects
    0.80
     overdue
    0.78
     voluntary
    0.77
     defaultdict
    0.76
     rated
    0.76
     mince
    0.74
    :)
    0.74
     DPI
    0.73
     outperformed
    0.73
    POSITIVE LOGITS
    Louisiana
    1.32
     Louisiana
    1.32
     louis
    1.24
    Alabama
    1.24
     Alabama
    1.14
     virginia
    1.13
    Iowa
    1.13
    loans
    1.07
    Texas
    1.05
    Missouri
    1.05
    Activations Density 0.004%

    No Known Activations