© 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. 22-GEMMASCOPE-RES-131K
    4. 68038
    Prev
    Next
    INDEX
    Explanations

    legal, social, and technical 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_22/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
    quelize
    -2.77
    最后由
    -1.97
     burgeoning
    -1.87
    廝
    -1.85
     داشتم
    -1.85
    tembro
    -1.85
     both
    -1.85
    鸶
    -1.83
    鸯
    -1.79
    鄖
    -1.77
    POSITIVE LOGITS
     But
    1.91
     magnificent
    1.67
     شهاد
    1.64
     رغم
    1.63
     monstrous
    1.60
     congreso
    1.59
     แต่
    1.59
     ใน
    1.53
    Compared
    1.49
     estamos
    1.47
    Activations Density 0.007%

    No Known Activations