© 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. 61436
    Prev
    Next
    INDEX
    Explanations

    mathematical formulas

    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
    луйста
    -1.56
     آن‌ها
    -1.55
    ൾ
    -1.45
     construite
    -1.45
     sosial
    -1.45
    れません
    -1.38
     by
    -1.36
    wnież
    -1.34
    茳
    -1.32
    ”，
    -1.31
    POSITIVE LOGITS
    普通の
    1.80
    一つの
    1.77
     you
    1.77
    慣れて
    1.73
     than
    1.63
     Vorschlag
    1.51
    柔ら
    1.50
    </strong>
    1.48
    驚く
    1.45
    そこに
    1.44
    Activations Density 0.017%

    No Known Activations