© 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. 59804
    Prev
    Next
    INDEX
    Explanations

    hstack, hiden, H(w), Houston

    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
     numerous
    -1.46
     commonly
    -1.33
    </h3>
    -1.31
     several
    -1.30
    ÑOS
    -1.29
     erklär
    -1.27
     så
    -1.26
     new
    -1.26
     small
    -1.24
     aberto
    -1.24
    POSITIVE LOGITS
     главе
    1.39
    Если
    1.32
     vrea
    1.30
     Sté
    1.29
     quelle
    1.28
    Мы
    1.27
    ätigung
    1.23
     eleva
    1.22
     законо
    1.20
     ferv
    1.19
    Activations Density 0.088%

    No Known Activations