© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 80932
    Prev
    Next
    INDEX
    Explanations

    insurance companies and organizations

    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_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
     vampires
    -0.82
     patatas
    -0.82
    mpz
    -0.81
    uun
    -0.81
     ARMY
    -0.80
    bahnhof
    -0.78
    droje
    -0.77
    thebibliography
    -0.76
    Carb
    -0.76
     Inventories
    -0.75
    POSITIVE LOGITS
     insurance
    4.13
     Insurance
    3.61
    Insurance
    3.30
    insurance
    3.17
     insurers
    3.13
     insurer
    3.11
     INSURANCE
    2.70
     страхо
    2.39
     insured
    2.34
    保険
    2.28
    Activations Density 0.061%

    No Known Activations