© 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. 98265
    Prev
    Next
    INDEX
    Explanations

    json "id" key

    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
     toffee
    -0.81
     व्या
    -0.79
    イング
    -0.78
    时
    -0.76
    ワイン
    -0.76
    上
    -0.73
    化した
    -0.73
    まで
    -0.71
    時
    -0.71
    答
    -0.71
    POSITIVE LOGITS
     string
    0.98
    string
    0.91
     Twitter
    0.88
    Str
    0.86
     thread
    0.85
    thread
    0.84
    xbc
    0.81
     STRING
    0.81
     String
    0.80
     str
    0.79
    Activations Density 0.005%

    No Known Activations