© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 43223
    Prev
    Next
    INDEX
    Explanations

    parenthetical phrases

    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
    ?
    -1.59
    Without
    -1.52
     onderdelen
    -1.47
    ‌.
    -1.46
    呗
    -1.43
    下一页
    -1.40
    .​
    -1.40
    ～　
    -1.38
    Through
    -1.38
     bacté
    -1.34
    POSITIVE LOGITS
     are
    1.66
    cić
    1.43
    ранее
    1.41
     Verwenden
    1.38
     可以
    1.35
     composta
    1.34
     Beobachtungen
    1.34
    突然
    1.34
    THERS
    1.33
     to
    1.32
    Activations Density 0.003%

    No Known Activations