© 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. 22-GEMMASCOPE-RES-131K
    7. 33769
    Prev
    Next
    INDEX
    Explanations

    legal representation statements

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

    The neuron activates on words referring to legal representatives (e.g., attorney, attorneys, counsel).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     diário
    -1.04
     ''
    -1.02
     decrees
    -0.96
     '';
    -0.94
    ajas
    -0.93
    ,''
    -0.89
    PREFACE
    -0.87
     its
    -0.87
     Tatsache
    -0.87
    ',
    -0.86
    POSITIVE LOGITS
     representing
    1.61
    representing
    1.40
     representar
    1.27
    Represent
    1.24
     client
    1.23
     Sloveniji
    1.19
     lawyers
    1.16
     clients
    1.16
     lawyer
    1.13
     team
    1.10
    Activations Density 0.096%

    No Known Activations