© 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. 119600
    Prev
    Next
    INDEX
    Explanations

    runs and scores

    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
     prét
    -1.36
    欒
    -1.35
     adiós
    -1.29
     它
    -1.28
    槙
    -1.27
     devaient
    -1.27
     aider
    -1.26
     afront
    -1.26
    お互
    -1.25
    omor
    -1.24
    POSITIVE LOGITS
    ↵
    1.47
     standalone
    1.43
    大多数
    1.30
     first
    1.29
    容易
    1.21
    hermoso
    1.21
     trovato
    1.20
    包括
    1.20
    包含
    1.20
    상
    1.19
    Activations Density 0.009%

    No Known Activations