© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 59341
    Prev
    Next
    INDEX
    Explanations

    leaders and leadership

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

    The neuron strongly activates on mentions of “leadership” and related hierarchical or authority contexts.

    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
    λισ
    -0.83
    дки
    -0.79
    target
    -0.79
     Morena
    -0.77
    ogaster
    -0.77
     Pompeo
    -0.77
    holde
    -0.76
    Ƅ
    -0.76
     сотрудники
    -0.75
    числен
    -0.75
    POSITIVE LOGITS
     leadership
    5.34
     leaders
    5.25
     leader
    4.69
    leadership
    3.70
     Leadership
    3.45
    leaders
    3.44
     Leaders
    3.41
    Leaders
    3.36
    Leadership
    3.33
     liderazgo
    3.25
    Activations Density 0.046%

    No Known Activations