© 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. 103068
    Prev
    Next
    INDEX
    Explanations

    FBI director

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

    The neuron strongly activates on references to U.S. government institutions and high-level officials (e.g. “FBI,” “Director,” “DoJ,” “Comey”).

    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
     Comcast
    -0.78
    grupo
    -0.76
    ieš
    -0.75
    anho
    -0.73
    ichy
    -0.73
    sitemap
    -0.72
    ̫
    -0.71
    行
    -0.71
    ₍
    -0.69
    iforn
    -0.69
    POSITIVE LOGITS
     stillness
    0.73
    rotter
    0.71
    ូ
    0.70
     termo
    0.70
     director
    0.69
     obsah
    0.69
    IALLY
    0.69
    čke
    0.68
    KAP
    0.68
     نمایند
    0.67
    Activations Density 0.004%

    No Known Activations