© 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. 65316
    Prev
    Next
    INDEX
    Explanations

    hashtags and product keywords

    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
     or
    -2.20
     and
    -2.06
     with
    -2.03
    appren
    -1.61
    फ़
    -1.58
     of
    -1.56
    franch
    -1.54
     in
    -1.51
     murieron
    -1.50
    😀
    -1.49
    POSITIVE LOGITS
    Spesifikasi
    2.02
    Kommentare
    1.92
    Качество
    1.90
    Inhalts
    1.77
    Полез
    1.72
    Langkah
    1.72
    냑
    1.70
     получает
    1.65
    Someone
    1.63
     logiciels
    1.60
    Activations Density 0.017%

    No Known Activations