© 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. 11247
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and equations

    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
    when
    -1.82
     entwickelte
    -1.65
     außerord
    -1.52
     excepto
    -1.47
    一个是
    -1.41
     productivo
    -1.41
     fordert
    -1.41
     about
    -1.39
    Also
    -1.37
    狀況
    -1.37
    POSITIVE LOGITS
    他的
    1.38
    其
    1.34
    çı
    1.34
     anillos
    1.34
    "¿
    1.33
    𓐍
    1.29
    <bos>
    1.28
     andere
    1.27
     halte
    1.27
    ≯
    1.23
    Activations Density 0.070%

    No Known Activations