© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 38662
    Prev
    Next
    INDEX
    Explanations

    math expressions and code elements

    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_22/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
     Willkommen
    -1.02
     クリア
    -1.00
    eip
    -0.98
     字符
    -0.98
     verbo
    -0.96
    Contenu
    -0.96
     favoris
    -0.96
    Musique
    -0.96
    袛
    -0.95
    inven
    -0.92
    POSITIVE LOGITS
     –
    1.09
    ～！
    1.05
     और
    0.97
    izmu
    0.96
    ILog
    0.91
     și
    0.90
     Desember
    0.89
    BigDecimal
    0.89
    isation
    0.87
    "./
    0.87
    Activations Density 0.029%

    No Known Activations