© 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. 65699
    Prev
    Next
    INDEX
    Explanations

    early numerical periods

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

    The neuron detects references to specific centuries or historical time periods (e.g. “19th” or “early 20th century”).

    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
    rungen
    -0.97
    前回の
    -0.94
     !!!!!
    -0.88
    ısında
    -0.88
    verhältnis
    -0.87
    odyne
    -0.86
     vijf
    -0.85
    ;}
    -0.84
     последний
    -0.84
     そば
    -0.83
    POSITIVE LOGITS
     early
    3.45
    early
    2.50
     Early
    2.28
    Early
    2.16
     frühen
    1.71
    EARLY
    1.60
     ран
    1.52
     EARLY
    1.50
     начале
    1.48
     início
    1.45
    Activations Density 0.046%

    No Known Activations