© 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. 22-GEMMASCOPE-RES-131K
    7. 11226
    Prev
    Next
    INDEX
    Explanations

    mathematical and scientific notation

    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_22/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
     verwacht
    -1.26
    づけ
    -1.17
    喏
    -1.15
     dezelfde
    -1.15
    も行
    -1.15
     goederen
    -1.13
     generó
    -1.13
    のではないか
    -1.12
     naast
    -1.08
     verbinding
    -1.08
    POSITIVE LOGITS
    が
    1.18
     in
    1.05
     (
    1.00
    を
    1.00
    no
    1.00
    。。。
    0.96
    參考資料
    0.93
    それも
    0.93
    、、
    0.92
    quer
    0.91
    Activations Density 0.015%

    No Known Activations