© 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. 11953
    Prev
    Next
    INDEX
    Explanations

    following significant events

    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
    </h1>
    -2.47
     to
    -2.17
    </i>
    -2.16
     has
    -2.13
    foglio
    -1.98
     vorhandenen
    -1.98
    {
    -1.91
    ’
    -1.91
    衣装
    -1.89
    会有
    -1.86
    POSITIVE LOGITS
    t
    2.30
    Karakteristik
    2.23
    Kelebihan
    2.16
    Kondisi
    2.11
    Spesifikasi
    2.06
    f
    2.05
    c
    2.03
    Sejarah
    2.03
    Semua
    1.97
    Siapa
    1.95
    Activations Density 0.003%

    No Known Activations