© 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. 70060
    Prev
    Next
    INDEX
    Explanations

    insurance, broker, agency roles

    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
    \{\\
    -0.75
     Mares
    -0.72
     falsche
    -0.70
     Maier
    -0.68
    yyyy
    -0.68
    jmp
    -0.67
     kimia
    -0.65
    ἥ
    -0.65
     deutsche
    -0.64
     сказ
    -0.63
    POSITIVE LOGITS
     broker
    1.59
     brokerage
    1.55
     Broker
    1.43
     brokers
    1.36
    broker
    1.34
     insurance
    1.23
    Broker
    1.20
     Brokers
    1.20
     Producer
    1.13
     agency
    1.09
    Activations Density 0.026%

    No Known Activations