© 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. 42430
    Prev
    Next
    INDEX
    Explanations

    boast of features

    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
     awaken
    -2.53
    ꦫ
    -2.39
    嶄
    -2.34
     esthétique
    -2.28
    никами
    -2.27
    ᗨ
    -2.27
    嗚
    -2.22
    elesai
    -2.19
     mutta
    -2.19
     последствия
    -2.17
    POSITIVE LOGITS
    {
    3.39
    0
    3.34
     hadapan
    2.61
    ’.
    2.45
    ;.
    2.44
    ".
    2.44
    both
    2.42
    
    2.38
    ,.
    2.38
    ↵
    2.38
    Activations Density 0.003%

    No Known Activations