© 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. 223149
    Prev
    Next
    INDEX
    Explanations

    consumer financial protection and regulation

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

    likely violations

    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
     emits
    0.47
     emitting
    0.46
    emit
    0.45
     Agri
    0.43
    emed
    0.43
     emit
    0.43
    秣
    0.43
    lake
    0.41
    emitting
    0.41
     mergeddata
    0.41
    POSITIVE LOGITS
     repayments
    0.40
     Ramsay
    0.40
    艰
    0.40
    τό
    0.40
     overdraft
    0.39
     thùng
    0.38
    艰难
    0.38
     repayment
    0.38
    教
    0.38
    ้าน
    0.38
    Activations Density 0.036%

    No Known Activations