© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 42783
    Prev
    Next
    INDEX
    Explanations

    proper nouns and acronyms

    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
     You
    -3.95
     are
    -2.67
     flatly
    -2.52
     signalled
    -2.31
    ors
    -2.25
     erweiter
    -2.22
     of
    -2.17
    1
    -2.17
    webtoken
    -2.16
     whereby
    -2.14
    POSITIVE LOGITS
    ઁ
    2.83
     می‌شود
    2.78
    呖
    2.75
    F
    2.64
    迓
    2.56
    ﻥ
    2.48
     твоя
    2.41
    買った
    2.39
    勿論
    2.38
    ínű
    2.34
    Activations Density 0.024%

    No Known Activations