© 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. 41603
    Prev
    Next
    INDEX
    Explanations

    top of the

    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
    しゃれ
    -1.33
    すすめ
    -1.30
    1
    -1.22
     الرسمي
    -1.21
    readFileSync
    -1.21
     gwia
    -1.21
     rijden
    -1.20
    がる
    -1.20
     vooral
    -1.20
    But
    -1.18
    POSITIVE LOGITS
     masing
    1.34
    Externé
    1.21
     hombros
    1.19
    老子
    1.17
     محمد
    1.17
    us
    1.17
     guapos
    1.16
     Они
    1.15
     mỗi
    1.15
     saying
    1.13
    Activations Density 0.018%

    No Known Activations