© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 42210
    Prev
    Next
    INDEX
    Explanations

    sparse matrix operations

    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
     same
    -1.61
     们
    -1.42
     auriculares
    -1.39
     reklam
    -1.28
     vidrio
    -1.27
     senderismo
    -1.23
    之战
    -1.23
    telah
    -1.21
     nhưng
    -1.19
    鸲
    -1.19
    POSITIVE LOGITS
     oscuros
    1.48
    statusBar
    1.34
    ות
    1.34
    ⇔
    1.26
    要
    1.20
     نداره
    1.20
    onatos
    1.19
     out
    1.18
    出て
    1.17
    СКИ
    1.17
    Activations Density 0.037%

    No Known Activations