© 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. 86743
    Prev
    Next
    INDEX
    Explanations

    quantities and units

    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
    isés
    -1.57
     brune
    -1.46
     but
    -1.45
     upra
    -1.40
     Frankrijk
    -1.40
     renou
    -1.38
     chimie
    -1.38
     sapatos
    -1.36
    isées
    -1.35
     bascul
    -1.35
    POSITIVE LOGITS
    是如何
    1.31
    程度上
    1.29
     один
    1.29
     گوید
    1.27
     всех
    1.27
     всички
    1.26
     semuanya
    1.26
    方法は
    1.25
    libat
    1.23
    是以
    1.23
    Activations Density 0.018%

    No Known Activations