© 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. 34-GEMMASCOPE-RES-131K
    7. 58122
    Prev
    Next
    INDEX
    Explanations

    political assembly members

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

    This neuron fires on programming code tokens—especially uppercase class/method names and configuration identifiers in C# (e.g. Configuration, NHibernate, ISessionFactory, Configure, SetProperty).

    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
     Senate
    -0.89
     senate
    -0.83
     Governor
    -0.79
     Wizard
    -0.75
     Schmidt
    -0.75
     sén
    -0.70
     रह
    -0.70
     ся
    -0.70
    мец
    -0.68
    osta
    -0.68
    POSITIVE LOGITS
     member
    1.16
    Majority
    1.02
    member
    0.88
    Member
    0.88
     MEMBER
    0.87
     Majority
    0.85
     DPRD
    0.85
    MEMBER
    0.83
     MEMBERS
    0.82
     assembly
    0.81
    Activations Density 0.015%

    No Known Activations