© 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. 34-GEMMASCOPE-RES-131K
    7. 116716
    Prev
    Next
    INDEX
    Explanations

    compound nouns

    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_34/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
    Jika
    -1.60
     erneut
    -1.54
     FUCK
    -1.53
     Jika
    -1.52
     также
    -1.46
     “…
    -1.43
    Ayrıca
    -1.42
    Дер
    -1.38
    上記の
    -1.38
    Въ
    -1.38
    POSITIVE LOGITS
     [
    2.63
     stuff
    2.50
     kind
    2.39
     things
    2.34
     somebody
    2.30
     thing
    2.13
     everybody
    2.09
     sort
    2.08
     maybe
    2.08
     really
    2.03
    Activations Density 0.025%

    No Known Activations