© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 54312
    Prev
    Next
    INDEX
    Explanations

    date ranges

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

    The neuron detects sequences of numbers (often days or years) connected by a hyphen—that is, numeric date or range expressions.

    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
    ၏
    -0.74
    戈
    -0.72
    update
    -0.72
    tired
    -0.70
    球迷
    -0.69
    mby
    -0.69
    armi
    -0.68
     Paar
    -0.68
    textView
    -0.68
     Point
    -0.68
    POSITIVE LOGITS
     Jude
    1.08
    職員
    0.80
    尖叫
    0.76
    Jude
    0.75
     Okan
    0.73
     Kingfisher
    0.70
     Bahrain
    0.68
     río
    0.67
     '*',
    0.67
    gadier
    0.67
    Activations Density 0.047%

    No Known Activations