© 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. 130641
    Prev
    Next
    INDEX
    Explanations

    foreign words

    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
     our
    -1.49
    =>"
    -1.13
     now
    -1.13
    =>'
    -1.13
     we
    -1.12
    🪛
    -1.09
    𓂂
    -1.09
    rückt
    -1.07
    וּ
    -1.06
    ־
    -1.05
    POSITIVE LOGITS
    Răspunde
    1.31
    あなた
    1.28
    Pengertian
    1.27
     Mère
    1.25
     eccl
    1.18
     deose
    1.17
    Kamu
    1.16
     Comédie
    1.13
    𝗼
    1.12
     bạn
    1.10
    Activations Density 0.000%

    No Known Activations