© 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. 82573
    Prev
    Next
    INDEX
    Explanations

    game controllers

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

    The neuron fires strongly on tokens that occur inside quotation marks—that is, it detects string‐literal contents.

    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
     Kanu
    -0.90
    спонд
    -0.76
     nuggets
    -0.75
     pinky
    -0.73
     Gorilla
    -0.73
     Nuggets
    -0.73
     townships
    -0.73
     PoE
    -0.70
     analyst
    -0.70
     AoE
    -0.70
    POSITIVE LOGITS
     controller
    3.59
     controllers
    3.33
    controller
    3.00
    Controller
    2.88
     Controller
    2.81
    controllers
    2.61
     Controllers
    2.48
    控制器
    2.45
    CONTROLLER
    2.27
    Controllers
    2.13
    Activations Density 0.017%

    No Known Activations