© 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. 61066
    Prev
    Next
    INDEX
    Explanations

    nested structures

    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
     fortalecer
    -1.20
     Passat
    -1.19
     DWORD
    -1.18
    遢
    -1.16
     pune
    -1.16
     tagħ
    -1.15
     pantaloni
    -1.14
     officio
    -1.14
     оказался
    -1.13
     couldn
    -1.13
    POSITIVE LOGITS
    Each
    1.38
    These
    1.23
    alucía
    1.19
    Should
    1.16
    责任编辑
    1.16
    리스
    1.16
    7
    1.14
    has
    1.13
     quiere
    1.13
     précieux
    1.13
    Activations Density 0.161%

    No Known Activations