© 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. 56
    Prev
    Next
    INDEX
    Explanations

    ultrasonic sensors and motors

    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
     This
    -3.08
     Which
    -2.86
     Want
    -2.69
     Whether
    -2.61
    ться
    -2.50
    鈇
    -2.48
     senjata
    -2.42
    
    -2.38
     algunas
    -2.36
    鳢
    -2.33
    POSITIVE LOGITS
     mani
    2.75
    𖣘
    2.72
    x
    2.50
    刂
    2.41
    Of
    2.41
     姆
    2.30
    榈
    2.30
    翃
    2.25
    $^\
    2.23
     achieves
    2.20
    Activations Density 0.004%

    No Known Activations