© 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. 30786
    Prev
    Next
    INDEX
    Explanations

    financial reports and accountancy

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

    The neuron is looking for numeric tokens—years, dollar amounts, percentages, dates, and other numeric figures.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    ographi
    -0.76
    兵
    -0.75
    hdys
    -0.74
     indexing
    -0.71
     <<"
    -0.71
    浴び
    -0.71
    ὲν
    -0.69
    шру
    -0.68
     кварти
    -0.68
    TextInputLayout
    -0.68
    POSITIVE LOGITS
     accounts
    2.95
    accounts
    2.39
    Accounts
    2.05
     Accounts
    1.98
     financial
    1.98
     annual
    1.89
     Annual
    1.70
     audited
    1.67
     comptes
    1.63
    financial
    1.54
    Activations Density 0.019%

    No Known Activations