© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 6723
    Prev
    Next
    INDEX
    Explanations

    refinance and refactor

    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
    nele
    -0.80
    mitas
    -0.72
    chèque
    -0.72
    ější
    -0.70
    ▂
    -0.69
    yolo
    -0.68
    탬
    -0.68
     grises
    -0.67
     beggar
    -0.67
    Orbit
    -0.67
    POSITIVE LOGITS
     refinancing
    3.80
     refinance
    3.55
     ref
    3.17
     refin
    3.17
     Refin
    2.83
    ref
    2.78
     Ref
    2.38
    Ref
    2.19
     refactor
    2.19
    REF
    1.94
    Activations Density 0.041%

    No Known Activations