© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 905
    Prev
    Next
    INDEX
    Explanations

    ahead of time or schedule

    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
    过来了
    -1.73
    replyreport
    -1.72
    两人的
    -1.65
    这场
    -1.63
    实话
    -1.61
    前辈
    -1.58
    教练
    -1.56
     the
    -1.53
    ↵
    -1.50
    发了
    -1.45
    POSITIVE LOGITS
    也
    1.91
     тоже
    1.80
    区分
    1.79
     sierp
    1.68
     batteri
    1.68
    луйста
    1.64
    un
    1.62
    if
    1.59
     dager
    1.57
    ."
    1.56
    Activations Density 0.002%

    No Known Activations