© 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. 105186
    Prev
    Next
    INDEX
    Explanations

    was/is followed by verb

    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
    และ
    -1.88
     that
    -1.85
     same
    -1.68
     и
    -1.67
     και
    -1.63
     those
    -1.56
     și
    -1.54
     و
    -1.51
     it
    -1.48
     swoje
    -1.45
    POSITIVE LOGITS
    Système
    1.44
     guardare
    1.41
    ↵
    1.39
     '
    1.35
    accompag
    1.34
     “,
    1.31
    Ouv
    1.31
     compla
    1.30
     Seorang
    1.30
     cuma
    1.30
    Activations Density 0.023%

    No Known Activations