© 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. 65816
    Prev
    Next
    INDEX
    Explanations

    past participles after "just" or "having"

    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
     arrivant
    -1.41
    这么
    -1.34
     héri
    -1.33
     Nevertheless
    -1.33
    从来没有
    -1.33
    繽
    -1.30
    ︕
    -1.30
     originaire
    -1.28
     frequentemente
    -1.28
     According
    -1.28
    POSITIVE LOGITS
     or
    1.62
     will
    1.49
     before
    1.44
    禿
    1.26
    武者
    1.26
    餉
    1.24
    …？
    1.23
     only
    1.23
     again
    1.23
    joner
    1.22
    Activations Density 0.222%

    No Known Activations