© 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. 10-GEMMASCOPE-RES-131K
    7. 60642
    Prev
    Next
    INDEX
    Explanations

    prepositions, verbs, and following words

    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
     our
    -1.93
     solchen
    -1.48
     nossa
    -1.46
     nuestro
    -1.41
     gelingt
    -1.39
    ↵
    -1.38
     nuestras
    -1.36
     entire
    -1.35
     your
    -1.34
     alem
    -1.34
    POSITIVE LOGITS
     who
    2.11
    鹮
    1.66
     údaj
    1.58
     acolo
    1.53
    ℟
    1.43
    AdvEx
    1.42
     whom
    1.40
     vardı
    1.40
    厉害
    1.39
    pixabay
    1.38
    Activations Density 0.020%

    No Known Activations