© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 99335
    Prev
    Next
    INDEX
    Explanations

    audit and accounting

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

    This neuron activates on formal standard or regulation citations that include a numbered designation (e.g. “ISA 230 Documentation”).

    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
    溅
    -1.01
     сутки
    -1.01
     блюда
    -0.92
     блюдо
    -0.88
     détails
    -0.88
    濺
    -0.84
     tarifs
    -0.82
     commerces
    -0.79
    ваку
    -0.79
     habe
    -0.79
    POSITIVE LOGITS
     audit
    1.45
     auditors
    1.41
     Accounting
    1.40
     auditor
    1.40
     accounting
    1.34
    audit
    1.34
     Audit
    1.33
    Accounting
    1.28
    Audit
    1.23
     accountants
    1.20
    Activations Density 0.022%

    No Known Activations