© 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. 57434
    Prev
    Next
    INDEX
    Explanations

    executive branches of government

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

    The neuron detects mentions of governmental institutions or branches (e.g. judiciary, executive, other government bodies).

    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
     overruled
    -0.79
    ционер
    -0.76
    quita
    -0.76
    protocols
    -0.74
     的
    -0.71
    řízení
    -0.71
    uebas
    -0.70
     inset
    -0.70
     oublié
    -0.69
     neuronal
    -0.69
    POSITIVE LOGITS
     executive
    2.78
     branch
    2.52
     branches
    2.42
     Executive
    2.34
    Executive
    2.17
    branch
    2.09
    executive
    2.08
    Branch
    2.06
     Branch
    2.05
     Branches
    1.96
    Activations Density 0.021%

    No Known Activations