© 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. 22-GEMMASCOPE-RES-131K
    7. 13435
    Prev
    Next
    INDEX
    Explanations

    incentives and rewards

    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
    Mutagenicity
    -0.93
     adieu
    -0.90
     gmbh
    -0.90
     容量
    -0.90
    Viitteet
    -0.89
     escorted
    -0.88
    няли
    -0.87
    Caracteristici
    -0.87
    HostException
    -0.86
     mika
    -0.86
    POSITIVE LOGITS
     rewards
    1.25
     reward
    1.24
     motivation
    1.14
     profit
    1.12
     prize
    1.11
     satisfaction
    1.09
     olsa
    1.05
     for
    1.04
     love
    0.98
     salary
    0.97
    Activations Density 0.027%

    No Known Activations