© 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. 360
    Prev
    Next
    INDEX
    Explanations

    YouTube links

    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
    潜水
    -0.79
     nogle
    -0.78
    konzert
    -0.77
    腭
    -0.73
     BCA
    -0.72
     Khusus
    -0.71
    endetta
    -0.71
    潜
    -0.70
     mapStateToProps
    -0.69
     سین
    -0.69
    POSITIVE LOGITS
     YouTube
    6.34
     youtube
    5.44
    YouTube
    5.28
     Youtube
    5.13
    youtube
    5.09
    Youtube
    4.63
     YOUTUBE
    3.53
    YOUTUBE
    3.33
    youtu
    3.09
     YT
    2.69
    Activations Density 0.066%

    No Known Activations