© 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. 129212
    Prev
    Next
    INDEX
    Explanations

    The neuron activates on insurance‐related terminology, especially specific insurance products and coverage types.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    insurance and protection

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     distritos
    -1.18
     Hinsicht
    -1.16
    Дереккөздер
    -1.16
    "$_
    -1.12
     econô
    -1.10
    chise
    -1.08
    acchar
    -1.04
    biendo
    -1.02
    rshire
    -1.02
     INFORMACIÓN
    -1.02
    POSITIVE LOGITS
     protection
    2.28
     coverage
    2.16
     protects
    1.73
     protecting
    1.70
     protect
    1.69
     insurance
    1.65
     your
    1.63
     for
    1.56
     Protection
    1.48
     protections
    1.43
    Activations Density 0.025%

    No Known Activations