© 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. 10-GEMMASCOPE-RES-131K
    7. 104060
    Prev
    Next
    INDEX
    Explanations

    Haberkip, 于昨日, TILL YOU

    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_10/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
    ?"
    -2.02
    最后由
    -1.93
    佯
    -1.88
     Dänemark
    -1.84
     عليك
    -1.84
    時間は
    -1.82
    〄
    -1.82
     která
    -1.82
    裡的
    -1.81
     Türen
    -1.80
    POSITIVE LOGITS
     the
    2.80
    s
    2.33
    Hmmm
    2.02
    mainly
    1.95
    有很多
    1.94
    jects
    1.93
    这样
    1.90
    ...
    1.89
    primarily
    1.86
    yeah
    1.85
    Activations Density 0.001%

    No Known Activations