© 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. 22-GEMMASCOPE-RES-131K
    7. 84496
    Prev
    Next
    INDEX
    Explanations

    abstract qualities followed by of

    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_22/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
     делает
    -1.41
    为什么
    -1.30
    怎样
    -1.27
     sirven
    -1.26
     برای
    -1.24
    UNICIP
    -1.23
    我可以
    -1.21
    ◷
    -1.20
    很多
    -1.20
    ⡠
    -1.19
    POSITIVE LOGITS
     of
    7.25
    ของ
    1.74
     that
    1.60
     של
    1.59
     của
    1.59
     των
    1.46
     OF
    1.46
     Of
    1.30
     της
    1.30
     it
    1.26
    Activations Density 0.053%

    No Known Activations