© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 31553
    Prev
    Next
    INDEX
    Explanations

    underwriting and lending

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ⋄
    -0.79
    Reparto
    -0.77
    iers
    -0.73
     Josephus
    -0.73
    الثة
    -0.73
    INDOW
    -0.73
    ~!
    -0.72
     Opa
    -0.71
    RESOURCES
    -0.71
    pio
    -0.71
    POSITIVE LOGITS
     underwriting
    3.78
     Under
    2.08
    Under
    1.95
    under
    1.54
    UNDER
    1.42
     UNDER
    1.39
     risk
    1.36
     Underwood
    1.33
     UW
    1.31
     origin
    1.26
    Activations Density 0.026%

    No Known Activations