© 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. 110534
    Prev
    Next
    INDEX
    Explanations

    relative clauses describing nouns

    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
     about
    -1.81
    </h2>
    -1.60
     mengucap
    -1.57
    l
    -1.55
    ).”
    -1.54
     ediyor
    -1.52
     same
    -1.47
    1
    -1.46
    al
    -1.45
    既に
    -1.44
    POSITIVE LOGITS
     küm
    1.64
    ឵
    1.62
    蹀
    1.60
    tedì
    1.52
    衚
    1.50
    reurs
    1.48
    до
    1.47
    wendi
    1.45
    และ
    1.45
    manteau
    1.45
    Activations Density 0.126%

    No Known Activations