© 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. 50349
    Prev
    Next
    INDEX
    Explanations

    Bolsheviks and Imperial Russia

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

    This neuron selectively activates on numerical tokens—especially years, dates, and other number sequences.

    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
    amela
    -0.79
     ||
    -0.75
     בישראל
    -0.73
     preview
    -0.72
     acrylic
    -0.72
     brasili
    -0.71
    외
    -0.70
    ovico
    -0.70
     {@
    -0.69
     benutzen
    -0.69
    POSITIVE LOGITS
     Whites
    1.27
    White
    1.12
     White
    1.09
     bandit
    1.01
     Bolshe
    1.00
    Whites
    1.00
    GPU
    0.98
     whites
    0.95
     Reds
    0.91
     WHITE
    0.89
    Activations Density 0.027%

    No Known Activations