© 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. 75623
    Prev
    Next
    INDEX
    Explanations

    quantities greater than

    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
     The
    -2.22
    -
    -1.99
    ↵↵
    -1.83
    咔
    -1.72
    蹦
    -1.69
     большого
    -1.67
     męskie
    -1.66
    ǧ
    -1.64
    忙碌
    -1.61
    真好
    -1.59
    POSITIVE LOGITS
     than
    3.16
    ματος
    2.13
    卹
    2.08
     importantly
    2.05
    銼
    1.94
    indrome
    1.93
     convinced
    1.92
     mayoría
    1.91
    謖
    1.90
     rengi
    1.88
    Activations Density 0.010%

    No Known Activations