© 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. 99805
    Prev
    Next
    INDEX
    Explanations

    social media platforms and the internet

    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
    strator
    -1.02
     YouTuber
    -0.93
    setMap
    -0.88
     cubo
    -0.86
    tikai
    -0.83
     TikTok
    -0.83
     herunterladen
    -0.83
     feltro
    -0.82
     袖
    -0.82
    اهش
    -0.82
    POSITIVE LOGITS
    便利な
    1.18
     platform
    1.14
    platform
    0.98
     democrati
    0.98
     addictive
    0.97
     where
    0.96
     handy
    0.95
     platforms
    0.94
    手軽
    0.93
     tools
    0.91
    Activations Density 0.056%

    No Known Activations