© 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. 10-GEMMASCOPE-RES-131K
    7. 84724
    Prev
    Next
    INDEX
    Explanations

    taxable income and benefits

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

    The neuron flags formal legal‐status and eligibility nouns—especially intellectual-property terms (e.g. patent, patentability, claims) and related rights/benefits words (e.g. compensation, benefits).

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     so
    -1.44
    ons
    -1.38
     assister
    -1.35
    撼
    -1.34
     physically
    -1.30
    re
    -1.26
     will
    -1.24
    os
    -1.23
     rendent
    -1.23
     drit
    -1.23
    POSITIVE LOGITS
     yılında
    1.49
     Aussehen
    1.47
    年には
    1.39
     when
    1.37
    remoto
    1.36
    當時
    1.34
    ंत्री
    1.30
     bekämp
    1.30
    tedy
    1.29
    atleta
    1.29
    Activations Density 0.052%

    No Known Activations