© 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. 42516
    Prev
    Next
    INDEX
    Explanations

    plume, Schwe, PLL, Elba, sque

    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
    ?”
    -2.98
    р
    -2.94
    и
    -2.27
    al
    -2.19
     برای
    -2.17
    н
    -2.16
    躂
    -2.16
            
    -2.14
     vivía
    -2.13
    र
    -2.13
    POSITIVE LOGITS
    衒
    2.58
     dekoratif
    2.42
    στημα
    2.39
    t
    2.38
    鵑
    2.36
     rajut
    2.33
     memasak
    2.27
    喽
    2.25
    スナー
    2.22
    ᭡
    2.20
    Activations Density 0.005%

    No Known Activations