© 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. 7112
    Prev
    Next
    INDEX
    Explanations

    track listing

    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
    дость
    -0.82
     clasific
    -0.82
     cláss
    -0.82
     olvides
    -0.81
    当選
    -0.80
    捺
    -0.80
     Bibel
    -0.77
    FileStream
    -0.77
     obligations
    -0.75
     Document
    -0.75
    POSITIVE LOGITS
     asemenea
    0.81
    Disc
    0.80
    作詞
    0.79
     vrijwilli
    0.79
     Wainwright
    0.78
     âmes
    0.78
    姆斯
    0.77
     êtres
    0.77
    パソコン
    0.77
    写真
    0.77
    Activations Density 0.015%

    No Known Activations