© 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. 32468
    Prev
    Next
    INDEX
    Explanations

    fugitive

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

    The neuron responds to the character sequence “fug,” marking words built on that root (e.g. fugitive, fugacity, fugue).

    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
    ULATION
    -0.87
    beiter
    -0.79
     forestry
    -0.75
    lying
    -0.73
    atization
    -0.72
     Luton
    -0.72
     حالی
    -0.71
    enschaft
    -0.71
    accessed
    -0.71
     Infinite
    -0.70
    POSITIVE LOGITS
    fug
    0.88
     fug
    0.87
     recovery
    0.82
     fugitive
    0.80
     Spending
    0.79
     Fug
    0.78
     diversité
    0.74
    Fug
    0.74
     Recovery
    0.73
     Conversations
    0.73
    Activations Density 0.046%

    No Known Activations