© 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. 12064
    Prev
    Next
    INDEX
    Explanations

    corporate names and suffixes

    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
     сам
    -1.24
     sevi
    -1.19
     if
    -1.16
     whether
    -1.09
     kat
    -1.08
     het
    -1.08
     ванной
    -1.08
    тий
    -1.06
    ている
    -1.05
     itself
    -1.05
    POSITIVE LOGITS
     帳
    1.48
     库存
    1.27
     厂家
    1.23
     台北
    1.20
     cesar
    1.20
     berdasarkan
    1.20
     Songtext
    1.19
     Wissenschaften
    1.19
     手順
    1.18
     dessas
    1.16
    Activations Density 0.109%

    No Known Activations