© 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. 103522
    Prev
    Next
    INDEX
    Explanations

    XML document attributes and declarations

    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
    マー
    -0.70
    変更
    -0.70
     <=
    -0.69
     agricole
    -0.68
     Irwin
    -0.67
     MK
    -0.66
     Huff
    -0.66
    型の
    -0.66
    dtype
    -0.65
     daytime
    -0.65
    POSITIVE LOGITS
    cipais
    0.68
    ără
    0.66
    unggah
    0.65
     Carn
    0.65
     preorder
    0.65
    峙
    0.65
    merkung
    0.65
    objetivo
    0.64
     PRS
    0.64
     effic
    0.64
    Activations Density 0.093%

    No Known Activations