© 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. 22-GEMMASCOPE-RES-131K
    7. 130286
    Prev
    Next
    INDEX
    Explanations

    The neuron flags words referring to espionage‐style deployment (sending agents, infiltration, spy activity).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    sent to investigate or arrive

    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
     zestawie
    -0.88
     personnalisées
    -0.88
    辦公
    -0.85
    瀰
    -0.83
    seende
    -0.83
    幫
    -0.83
     elétrico
    -0.81
    诙
    -0.80
    HasColumnName
    -0.79
     bő
    -0.79
    POSITIVE LOGITS
     to
    2.39
     tasked
    1.19
    Cuáles
    1.03
     भे
    1.01
     investigate
    1.01
    ærk
    0.96
    aisons
    0.93
    PushMatrix
    0.92
    公平
    0.91
    sent
    0.90
    Activations Density 0.043%

    No Known Activations