© 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. 75323
    Prev
    Next
    INDEX
    Explanations

    Slavic and Eastern European surnames

    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
    </b>
    -1.74
    n
    -1.61
     as
    -1.50
     beschäf
    -1.44
    有时
    -1.43
    不论
    -1.41
    一方で
    -1.38
    巿
    -1.38
     benötigen
    -1.37
    ing
    -1.35
    POSITIVE LOGITS
    ༈
    1.65
     Kalifor
    1.59
    enced
    1.59
    omato
    1.55
     kork
    1.52
    yled
    1.52
    nemu
    1.51
     magie
    1.51
    清新
    1.47
    蚰
    1.45
    Activations Density 0.050%

    No Known Activations