© 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. 69146
    Prev
    Next
    INDEX
    Explanations

    contract

    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
     terão
    -1.91
    
    -1.89
     ‘‘
    -1.83
     музыка
    -1.81
    甗
    -1.79
    ޏ
    -1.78
     放題
    -1.77
    鲧
    -1.72
     weiße
    -1.71
    ⢂
    -1.71
    POSITIVE LOGITS
     is
    2.52
    但他
    1.83
    ---
    1.81
    er
    1.77
     to
    1.76
     jeweiligen
    1.74
     These
    1.72
    ?"
    1.71
     BOTH
    1.71
    i
    1.70
    Activations Density 0.021%

    No Known Activations