© 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. 94001
    Prev
    Next
    INDEX
    Explanations

    stock ticker symbols

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

    The neuron primarily activates on numeric tokens and numeric sequences (e.g., multi‐digit numbers and stock‐ticker–style numeric/alphanumeric strings).

    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
     desagrad
    -0.91
     ה
    -0.89
    namb
    -0.84
    isip
    -0.81
     enjoyable
    -0.80
    ztály
    -0.80
     sirva
    -0.79
    APON
    -0.78
    music
    -0.77
    Hogyan
    -0.77
    POSITIVE LOGITS
     Sense
    1.09
     Nifty
    0.93
     Danemark
    0.86
     BSE
    0.85
     PSU
    0.85
     realty
    0.80
    Croatia
    0.79
     frontline
    0.77
     نکرد
    0.77
     Guilty
    0.76
    Activations Density 0.002%

    No Known Activations