© 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. 61064
    Prev
    Next
    INDEX
    Explanations

    list delimiters

    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
     发表于
    -1.29
     моих
    -1.22
    嚷
    -1.17
     ตั้ง
    -1.14
    viele
    -1.13
    LEY
    -1.10
    在这里
    -1.10
    much
    -1.09
    every
    -1.09
    唐揚げ
    -1.08
    POSITIVE LOGITS
     when
    2.13
     even
    1.38
     most
    1.30
     детям
    1.28
     relatively
    1.27
     people
    1.27
     if
    1.23
    “
    1.22
     satisfactory
    1.20
    onStop
    1.20
    Activations Density 0.035%

    No Known Activations