© 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. 59575
    Prev
    Next
    INDEX
    Explanations

    American founding and revolutionary history

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

    The neuron is simply a “reading‐head” for document position—it ramps up activation the farther into the text you get, regardless of the word itself.

    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
     udrž
    -0.93
     Socialists
    -0.93
     chauffeur
    -0.89
     socialists
    -0.86
    NTSTATUS
    -0.85
     Predators
    -0.84
     rodzaju
    -0.84
    Děkuji
    -0.82
    lmao
    -0.81
    Alberta
    -0.81
    POSITIVE LOGITS
     Founding
    1.95
     Revolutionary
    1.93
     America
    1.80
     Declaration
    1.76
     Jefferson
    1.63
     founding
    1.52
    Declaration
    1.50
     colonists
    1.48
    Revolutionary
    1.46
     Constitution
    1.44
    Activations Density 0.097%

    No Known Activations