© 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. 2262
    Prev
    Next
    INDEX
    Explanations

    PlayStation, PSP, Vita

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

    The neuron detects references to PlayStation products or the “PS” gaming platform.

    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
    Wii
    -0.87
     Wii
    -0.83
    readdir
    -0.79
    aulted
    -0.78
    quill
    -0.76
    ampi
    -0.73
     ED
    -0.71
     xml
    -0.71
     Ukrainian
    -0.69
     exposure
    -0.69
    POSITIVE LOGITS
     PSP
    1.37
    PSP
    1.16
     PSM
    0.99
     Xperia
    0.97
     Vita
    0.97
     psp
    0.93
     PSE
    0.88
    Cyprus
    0.88
     PSN
    0.87
     Catalina
    0.84
    Activations Density 0.019%

    No Known Activations