© 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. 38677
    Prev
    Next
    INDEX
    Explanations

    military district units

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

    The neuron is keyed to numeric and ordinal tokens (years, digits, “1st,” etc.), especially when they appear in parentheses or as part of formal designations.

    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
    ovico
    -0.86
    zentrum
    -0.82
    ENCES
    -0.79
     céramique
    -0.79
    混沌
    -0.78
    哇
    -0.78
    gemeinschaft
    -0.77
    rechnung
    -0.76
    scriptcase
    -0.76
    ്യ
    -0.75
    POSITIVE LOGITS
     underground
    0.93
     Guer
    0.90
    guer
    0.88
     liberated
    0.88
     Kid
    0.87
     operational
    0.87
     collegamento
    0.86
     cadres
    0.86
     command
    0.84
    vanou
    0.84
    Activations Density 0.017%

    No Known Activations