© 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. 101771
    Prev
    Next
    INDEX
    Explanations

    benevolent, omnipresent, pluripotent

    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
    皲
    -2.27
    München
    -2.20
    -2.20
    sonaro
    -2.19
    ла
    -2.13
    笮
    -2.13
     \'
    -2.09
    end
    -2.09
     \"
    -2.05
     disparate
    -2.05
    POSITIVE LOGITS
    We
    3.09
    鹟
    2.61
    {
    2.56
    *
    2.38
    </sup>
    2.28
    .
    2.22
    這
    2.16
    鹇
    2.05
    儇
    2.00
    可能
    1.96
    Activations Density 0.005%

    No Known Activations