© 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. 75682
    Prev
    Next
    INDEX
    Explanations

    android list items

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

    The neuron is detecting numeric literals (sequences of digits) in the code or XML.

    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
    Fight
    -0.94
    ár
    -0.90
     粒
    -0.88
    ญี่ป
    -0.88
     ensimmä
    -0.87
    telse
    -0.87
    gården
    -0.86
    🏗
    -0.86
    LOGIN
    -0.84
    Teks
    -0.84
    POSITIVE LOGITS
     list
    1.71
     history
    1.64
     recent
    1.48
     History
    1.33
     available
    1.32
     Recent
    1.28
    History
    1.27
    history
    1.27
     cities
    1.20
     selected
    1.20
    Activations Density 0.034%

    No Known Activations