© 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. 57277
    Prev
    Next
    INDEX
    Explanations

    antagonists and authority figures

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

    The neuron fires on references to specific named entities—proper nouns like character names, titles, locations, or other unique identifiers in the text.

    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
    ^[
    -0.77
     heroic
    -0.75
    ssan
    -0.75
     saints
    -0.75
     healer
    -0.75
    仵
    -0.75
    ショナル
    -0.75
     legends
    -0.74
    eynman
    -0.74
     funciones
    -0.73
    POSITIVE LOGITS
     antagonist
    1.05
     Voldemort
    1.05
     Thanos
    1.00
    Councillor
    0.92
    Rever
    0.90
     antagonists
    0.88
     Commandant
    0.86
     Bowser
    0.85
     Administrator
    0.85
    Darth
    0.82
    Activations Density 0.066%

    No Known Activations