© 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. 75087
    Prev
    Next
    INDEX
    Explanations

    flat disks or shapes

    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
     they
    -1.51
    REGUL
    -1.29
     brachten
    -1.27
     accus
    -1.22
     atualmente
    -1.21
    AVL
    -1.20
    Ache
    -1.20
     Además
    -1.17
     roy
    -1.16
    Piotr
    -1.16
    POSITIVE LOGITS
    G
    1.44
    H
    1.40
    इटम
    1.40
    S
    1.37
    Q
    1.34
    Thanks
    1.32
    One
    1.30
    Both
    1.28
     ".";
    1.28
    Flat
    1.27
    Activations Density 0.121%

    No Known Activations