© 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. 20
    Prev
    Next
    INDEX
    Explanations

    post- words

    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
     are
    -2.39
     zwanzig
    -2.27
     to
    -2.20
    鹋
    -2.17
    也得
    -1.98
    摒
    -1.98
    氿
    -1.95
     zwölf
    -1.90
     This
    -1.84
    fantasia
    -1.81
    POSITIVE LOGITS
    Очень
    2.36
    桖
    2.31
    s
    2.14
     現貨
    2.09
     russes
    2.05
    i
    2.05
    櫚
    2.05
    鞴
    2.05
    Setelah
    2.02
    Пусть
    2.02
    Activations Density 0.025%

    No Known Activations