© 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. 19153
    Prev
    Next
    INDEX
    Explanations

    about systems

    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
     但
    -1.55
    SPECTION
    -1.52
    臜
    -1.50
    鼍
    -1.45
     bezw
    -1.45
    雯
    -1.45
    zerű
    -1.43
     gier
    -1.42
    IONAL
    -1.41
    ſſel
    -1.39
    POSITIVE LOGITS
     them
    1.57
     でも
    1.56
    them
    1.54
     ‘‘
    1.46
    سرائ
    1.44
    ࿚
    1.44
     situations
    1.41
    仕方
    1.41
    t
    1.41
    理由は
    1.38
    Activations Density 0.091%

    No Known Activations