© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 110959
    Prev
    Next
    INDEX
    Explanations

    liability coverage

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

    This neuron detects insurance-and-liability jargon—terms and phrases about being insured/licensed, insurance policies, compensation or responsibility.

    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
    就算是
    -0.79
     ModelExpression
    -0.78
    promotion
    -0.76
    %=
    -0.76
     Promotion
    -0.75
    สิทธิ
    -0.75
    ustice
    -0.74
     promotion
    -0.73
    ichen
    -0.73
     sukienka
    -0.72
    POSITIVE LOGITS
     coverage
    1.15
    proof
    1.13
     proof
    1.12
    coverage
    1.05
     naming
    1.05
    Proof
    1.03
     liability
    1.03
    limits
    0.94
    naming
    0.94
     limits
    0.92
    Activations Density 0.014%

    No Known Activations