© 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. 12575
    Prev
    Next
    INDEX
    Explanations

    words starting with Mag

    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
    夘
    -2.69
     großes
    -2.64
    袮
    -2.59
    乆
    -2.55
    铡
    -2.48
    是怎么
    -2.48
    了的
    -2.45
    熘
    -2.45
    ated
    -2.41
     tuviera
    -2.41
    POSITIVE LOGITS
     increase
    2.66
     这个
    2.64
    a
    2.58
    有點
    2.56
     ensure
    2.42
     можно
    2.38
    家の
    2.27
     primeiras
    2.27
    牆
    2.25
     SOME
    2.23
    Activations Density 0.023%

    No Known Activations