© 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. 21802
    Prev
    Next
    INDEX
    Explanations

    article starting noun phrases

    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
     to
    -2.42
     you
    -1.79
     like
    -1.70
     these
    -1.70
     at
    -1.55
     by
    -1.45
     there
    -1.45
     as
    -1.45
    eronau
    -1.43
     and
    -1.40
    POSITIVE LOGITS
     ۸
    1.65
     “(
    1.55
     anún
    1.55
     “[
    1.54
    چنین
    1.50
     vacacionales
    1.49
     !(
    1.48
    氽
    1.48
     ۱۲
    1.46
     gustó
    1.46
    Activations Density 0.029%

    No Known Activations