© 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. 93459
    Prev
    Next
    INDEX
    Explanations

    contracts and enforcement

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

    Explanation of neuron 4 behavior: the main thing this neuron does is find mentions of “contract” (and its closely related forms) in legal text.

    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
    kosten
    -0.88
    خار
    -0.84
    staat
    -0.82
    jante
    -0.81
    Pv
    -0.80
    ftances
    -0.78
    无关
    -0.78
     bridegroom
    -0.77
    stanza
    -0.77
     THESIS
    -0.73
    POSITIVE LOGITS
     enforce
    1.53
     enforceable
    1.37
     contract
    1.37
     contracts
    1.34
     oral
    1.29
     enforcement
    1.20
     Contract
    1.15
    enforce
    1.10
     Contracts
    1.10
     formation
    1.09
    Activations Density 0.022%

    No Known Activations