© 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. 2009
    Prev
    Next
    INDEX
    Explanations

    tax reporting and financial statements

    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
     at
    -0.76
     заря
    -0.75
     tied
    -0.74
    KR
    -0.74
    urtstag
    -0.70
     zwaar
    -0.70
     FSB
    -0.70
    FC
    -0.69
     Index
    -0.69
    Index
    -0.69
    POSITIVE LOGITS
     TDS
    0.89
     reporting
    0.87
    adeloupe
    0.82
    TDS
    0.80
     REPORTING
    0.79
     magnético
    0.79
     berichtet
    0.78
     TIN
    0.78
     trzec
    0.78
    Statements
    0.77
    Activations Density 0.012%

    No Known Activations