© 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. 53923
    Prev
    Next
    INDEX
    Explanations

    social media platforms

    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
     on
    -1.54
     trên
    -1.47
    บน
    -1.23
     на
    -1.15
    在
    -1.10
     روی
    -1.02
     kwenye
    -0.97
    際には
    -0.95
    Unless
    -0.93
    いざ
    -0.91
    POSITIVE LOGITS
     platform
    1.13
    platforms
    1.12
     platforms
    1.05
    meiras
    0.98
    platform
    0.98
    💻
    0.94
    平台
    0.94
     where
    0.92
     světě
    0.92
    ignée
    0.90
    Activations Density 0.112%

    No Known Activations