© 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. 1371
    Prev
    Next
    INDEX
    Explanations

    setting innerHTML or describing thickness

    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
     ingrained
    -3.16
    蛧
    -2.92
    When
    -2.73
    تیجه
    -2.70
     odeur
    -2.70
     unrelenting
    -2.59
    There
    -2.56
    Going
    -2.55
     continual
    -2.55
    她
    -2.53
    POSITIVE LOGITS
     of
    3.61
    是这样
    2.95
     dando
    2.63
     tht
    2.61
    はその
    2.59
    是自己
    2.58
     ite
    2.48
    霂
    2.47
     หลัง
    2.47
     focuses
    2.47
    Activations Density 0.005%

    No Known Activations