© 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. 10-GEMMASCOPE-RES-131K
    7. 80596
    Prev
    Next
    INDEX
    Explanations

    PlayStation generations

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

    The neuron detects mentions of video‐game console platforms, i.e. console abbreviations coupled with generation numbers (e.g. “PS3,” “PS4,” “Xbox One,” etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    谖
    -2.42
    ࿚
    -2.22
    賔
    -2.13
    ࿊
    -2.02
    祘
    -2.00
     ‚
    -1.93
    旆
    -1.91
    إنه
    -1.91
     いち
    -1.90
    ݯ
    -1.87
    POSITIVE LOGITS
    我们
    1.69
     dengan
    1.67
     dasarnya
    1.65
    '
    1.59
    inderung
    1.58
     môže
    1.55
    with
    1.52
     weiße
    1.49
     машине
    1.49
    幸运
    1.48
    Activations Density 0.005%

    No Known Activations