© 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. 12526
    Prev
    Next
    INDEX
    Explanations

    applications

    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
    yelitis
    -2.14
    acterium
    -1.85
    鲠
    -1.78
     ſaid
    -1.78
    〖
    -1.70
    coltura
    -1.64
    grafa
    -1.63
    怄
    -1.61
    肪
    -1.59
     チョ
    -1.59
    POSITIVE LOGITS
    7
    3.39
    3
    2.83
    1
    2.83
    0
    2.70
    6
    2.39
    8
    2.38
    4
    2.34
    ２
    2.34
    5
    2.28
    
    2.23
    Activations Density 0.028%

    No Known Activations