© 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. 42863
    Prev
    Next
    INDEX
    Explanations

    onomatopoeia and sounds

    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
     need
    -1.87
     to
    -1.71
    觏
    -1.57
    殽
    -1.48
     bulunabilir
    -1.48
     delicacy
    -1.47
     transmissão
    -1.46
     attesa
    -1.43
     Veränderungen
    -1.42
     desempenho
    -1.41
    POSITIVE LOGITS
    ҫ
    1.42
    nikami
    1.32
    vaných
    1.32
    _->
    1.31
    ѕ
    1.31
     voulait
    1.30
    하였다
    1.30
    nthesis
    1.30
    为啥
    1.28
     они
    1.27
    Activations Density 0.033%

    No Known Activations