© 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. 59937
    Prev
    Next
    INDEX
    Explanations

    video game console versions

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

    The neuron is detecting mentions of gaming platforms or console/PC hardware names (often with associated abbreviations or model identifiers).

    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
    様の
    -0.99
    theft
    -0.88
    glazed
    -0.86
     kinds
    -0.86
    chiato
    -0.82
    沨
    -0.82
    SanPham
    -0.82
    altro
    -0.81
    macbook
    -0.81
    様が
    -0.80
    POSITIVE LOGITS
     version
    1.29
    exclusive
    1.22
    版
    1.21
    Exclusive
    1.08
     owners
    1.08
    上的
    1.06
     exclusive
    1.02
     port
    1.00
     ports
    0.97
    ilí
    0.97
    Activations Density 0.036%

    No Known Activations