© 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. 13380
    Prev
    Next
    INDEX
    Explanations

    to + verb, in + noun

    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
    Моя
    -1.29
    Последние
    -1.27
    各样的
    -1.25
    Приятного
    -1.22
     nyeri
    -1.21
    部件
    -1.21
     también
    -1.18
    נחנו
    -1.18
    сшта
    -1.17
     kuhusu
    -1.16
    POSITIVE LOGITS
    igem
    1.22
    婶
    1.20
    ._.
    1.19
    暧
    1.16
     правительства
    1.16
    了许多
    1.16
     to
    1.15
    roon
    1.09
    [!
    1.08
     столь
    1.05
    Activations Density 0.043%

    No Known Activations