© 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. 77629
    Prev
    Next
    INDEX
    Explanations

    home and commercial insurance

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

    The neuron detects mentions of insurance products or policies (e.g. “Home Insurance,” “Buildings & Contents,” “policy,” “insurance broker,” etc.).

    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
    supplement
    -0.84
    examen
    -0.72
     converti
    -0.71
    哽
    -0.70
     supplement
    -0.70
     farma
    -0.69
     マン
    -0.69
    Df
    -0.69
     simbo
    -0.69
     لق
    -0.68
    POSITIVE LOGITS
     insurance
    1.26
     Insurance
    1.13
     insurer
    1.11
     insurers
    1.09
     insuring
    1.08
    Insurance
    1.06
     Brokers
    1.05
     brokers
    1.02
    insurance
    1.01
     uninsured
    0.98
    Activations Density 0.014%

    No Known Activations