© 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. 38694
    Prev
    Next
    INDEX
    Explanations

    gaming consoles or hardware

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

    The neuron is detecting tokens that are largely numerals or uppercase‐letter sequences (e.g. numbers, acronyms, all-caps words, and title headings).

    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
    rások
    -0.94
    ὑ
    -0.90
    NCBI
    -0.90
     Sustainable
    -0.89
    erein
    -0.87
    هة
    -0.87
     leuk
    -0.85
    ↻
    -0.85
    шай
    -0.84
    doin
    -0.84
    POSITIVE LOGITS
     console
    1.45
     games
    1.43
     consoles
    1.34
     Wii
    1.34
     Nintendo
    1.20
     Japão
    1.15
    Console
    1.14
    Wii
    1.13
     hardware
    1.12
     Console
    1.09
    Activations Density 0.105%

    No Known Activations