© 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. 34-GEMMASCOPE-RES-131K
    7. 84176
    Prev
    Next
    INDEX
    Explanations

    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
     estatua
    -0.92
     puerta
    -0.79
    搞
    -0.75
     ТВ
    -0.75
     niin
    -0.75
    politico
    -0.74
     sienta
    -0.74
    soni
    -0.74
    钵
    -0.73
    Balls
    -0.73
    POSITIVE LOGITS
     internet
    4.81
     Internet
    4.63
    Internet
    3.91
    internet
    3.83
     INTERNET
    2.94
    INTERNET
    2.86
    互联网
    2.81
     интернет
    2.59
    インターネット
    2.58
    ترنت
    2.20
    Activations Density 0.075%

    No Known Activations