© 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. 55840
    Prev
    Next
    INDEX
    Explanations

    numbers after than or over

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

    The neuron strongly activates on multi-digit numeric tokens—especially years.

    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
     in
    -1.01
    Two
    -0.97
     now
    -0.97
    Every
    -0.96
    Before
    -0.94
    Shortly
    -0.94
     by
    -0.93
    When
    -0.92
     comes
    -0.91
    Following
    -0.91
    POSITIVE LOGITS
     years
    1.55
     strá
    1.01
     suốt
    0.99
     boyunca
    0.98
    carus
    0.98
     months
    0.97
    ''''
    0.95
     Spent
    0.94
    ifica
    0.93
    beria
    0.93
    Activations Density 0.063%

    No Known Activations