Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 7836
    Prev
    Next
    INDEX
    Explanations

    virtual reality controllers and tracking

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    وانی
    -0.76
    挨
    -0.75
    鼠标
    -0.75
    mobili
    -0.74
     mobili
    -0.74
    期的
    -0.73
    ências
    -0.73
     chilli
    -0.72
     пакет
    -0.72
    酒
    -0.71
    POSITIVE LOGITS
     controllers
    1.14
     tracking
    1.11
     tracked
    1.05
     Steam
    0.98
     Controllers
    0.97
    Steam
    0.96
     Tracking
    0.93
     controller
    0.93
     Valve
    0.89
    controllers
    0.88
    Activations Density 0.026%

    No Known Activations