© 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. 97829
    Prev
    Next
    INDEX
    Explanations

    uploading and posting photos

    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
    tweets
    -0.91
    印刷
    -0.82
    ifflin
    -0.82
     tivi
    -0.81
    plugins
    -0.81
     filtres
    -0.78
    HEA
    -0.78
     ليب
    -0.78
    ","+
    -0.77
    ি
    -0.77
    POSITIVE LOGITS
     upload
    1.85
     uploading
    1.69
    upload
    1.45
    photobucket
    1.45
     resizing
    1.43
     resized
    1.40
     uploads
    1.38
     resize
    1.38
     uploaded
    1.33
     posting
    1.25
    Activations Density 0.022%

    No Known Activations