© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 110718
    Prev
    Next
    INDEX
    Explanations

    data and programming contexts

    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
    lijden
    -1.00
    Seznam
    -0.98
     prominent
    -0.98
     by
    -0.97
    Condol
    -0.97
    Surprisingly
    -0.95
    ванием
    -0.94
     an
    -0.94
     Flughafen
    -0.94
     Using
    -0.93
    POSITIVE LOGITS
     data
    2.47
    data
    1.98
    DATA
    1.41
     데이터
    1.35
    ข้อมูล
    1.34
    数据
    1.26
     datter
    1.23
     данным
    1.22
     Abonnez
    1.18
     food
    1.16
    Activations Density 0.060%

    No Known Activations