© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 31850
    Prev
    Next
    INDEX
    Explanations

    Android rooting and ROMs

    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
     комп
    -1.06
    savevideo
    -1.02
    鼠标
    -1.00
    ฿
    -0.97
    readFileSync
    -0.97
    WEBPACK
    -0.96
     chatbot
    -0.96
    oredCriteria
    -0.96
     ноутбу
    -0.94
    issão
    -0.93
    POSITIVE LOGITS
     Android
    1.63
     rooted
    1.41
     android
    1.38
    rooted
    1.28
     OTA
    1.26
     ROM
    1.23
    Droid
    1.22
     rooting
    1.20
    Android
    1.20
    android
    1.20
    Activations Density 0.198%

    No Known Activations