© 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. 22-GEMMASCOPE-RES-131K
    7. 104383
    Prev
    Next
    INDEX
    Explanations

    transition to new sentence

    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_22/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
     anden
    -1.00
     verband
    -1.00
     istället
    -0.99
    🍸
    -0.99
     tempel
    -0.98
     zó
    -0.96
    isim
    -0.93
     foran
    -0.93
     rivi
    -0.92
    pout
    -0.92
    POSITIVE LOGITS
     but
    2.33
    However
    2.20
     however
    2.14
     However
    2.05
     allerdings
    1.66
    Однако
    1.63
     však
    1.63
    ただし
    1.60
     jedoch
    1.57
     azonban
    1.54
    Activations Density 0.066%

    No Known Activations