© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 58053
    Prev
    Next
    INDEX
    Explanations

    tax deductions and credits

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

    The neuron is detecting references to tax deductions, credits, or other tax-relief terms.

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     даже
    -1.89
    )
    -1.74
    t
    -1.60
    \
    -1.60
    x
    -1.59
    Not
    -1.57
    In
    -1.55
    j
    -1.55
    l
    -1.53
    _
    -1.53
    POSITIVE LOGITS
    
    1.82
    ᯾
    1.73
     desconhe
    1.68
     respald
    1.55
     desconoc
    1.51
    regalo
    1.50
     estric
    1.48
     debajo
    1.48
     somente
    1.46
     talvez
    1.46
    Activations Density 0.006%

    No Known Activations