© 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. 105067
    Prev
    Next
    INDEX
    Explanations

    modal verbs followed by verbs

    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
     When
    -1.48
     The
    -1.45
    ࿚
    -1.41
    了你
    -1.41
    ！”
    -1.35
     probably
    -1.34
    鯷
    -1.32
     undoubtedly
    -1.31
    ！！”
    -1.31
     This
    -1.28
    POSITIVE LOGITS
     つの
    1.52
    寻求
    1.48
     古い
    1.39
    一闪
    1.36
    るの
    1.32
     envoie
    1.32
    さぎ
    1.30
     sicherzustellen
    1.29
     of
    1.27
    々は
    1.23
    Activations Density 0.026%

    No Known Activations