© 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. 85192
    Prev
    Next
    INDEX
    Explanations

    stdint.h includes

    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
    ⿳
    -1.42
     it
    -1.42
     Vorsitzender
    -1.26
    这
    -1.25
    🍖
    -1.25
     arī
    -1.22
    ynchro
    -1.21
    It
    -1.21
     איך
    -1.19
    ⿴
    -1.19
    POSITIVE LOGITS
     other
    1.64
     comprends
    1.49
    男人的
    1.45
     different
    1.41
    tigma
    1.38
    早已
    1.34
    勿論
    1.34
    今でも
    1.33
     такую
    1.33
     speichern
    1.33
    Activations Density 0.013%

    No Known Activations