© 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. 123936
    Prev
    Next
    INDEX
    Explanations

    mobile, iPhone, bumper

    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_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
     It
    -1.90
     religieux
    -1.84
     блюдо
    -1.84
     растений
    -1.77
     we
    -1.76
     الجلد
    -1.75
     I
    -1.75
     النبات
    -1.74
     this
    -1.73
     włosów
    -1.73
    POSITIVE LOGITS
    וּ
    2.95
    ּוֹ
    2.52
     бампер
    2.33
    ᾽
    2.23
    ִּ
    2.20
    ҉
    2.13
     آیفون
    2.03
    ֶּ
    2.02
     موبایل
    1.95
    ᾿
    1.95
    Activations Density 0.116%

    No Known Activations