© 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. 65362
    Prev
    Next
    INDEX
    Explanations

    Kab, Kabul, Buk, Kag

    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
    摃
    -2.67
    ll
    -2.63
     wiele
    -2.53
     '
    -2.48
     feiner
    -2.44
     meisten
    -2.38
     =
    -2.38
     jeopardi
    -2.31
    es
    -2.28
     моя
    -2.25
    POSITIVE LOGITS
     短发
    2.59
    牁
    2.45
     wortel
    2.42
    盦
    2.33
     poë
    2.33
    .&
    2.28
     estadounid
    2.27
    婓
    2.25
    幛
    2.23
     nadru
    2.20
    Activations Density 0.003%

    No Known Activations