© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 1349
    Prev
    Next
    INDEX
    Explanations

    source code license terms

    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
    Rés
    -0.92
    quested
    -0.84
    Andra
    -0.83
    スポンサーリンク
    -0.80
     sorgfäl
    -0.80
    おはようございます
    -0.80
     spelen
    -0.80
    锯
    -0.79
    こんばんは
    -0.79
     计划
    -0.77
    POSITIVE LOGITS
    ↵
    0.97
    were
    0.94
    nil
    0.92
    avatar
    0.91
    rea
    0.85
     dokumenti
    0.84
    }</
    0.84
    Longrightarrow
    0.84
    cale
    0.82
    η
    0.81
    Activations Density 0.074%

    No Known Activations