© 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. 28453
    Prev
    Next
    INDEX
    Explanations

    time durations

    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
     this
    -1.22
    :
    -1.13
     ezek
    -1.13
    niejsza
    -1.08
     that
    -1.05
    はこちらから
    -1.02
    に行ってきました
    -1.02
     a
    -1.02
    êté
    -1.00
    ヶ月
    -0.96
    POSITIVE LOGITS
     then
    1.64
    Then
    1.48
     если
    1.30
     puis
    1.23
     чтобы
    1.16
    then
    1.16
     paperback
    1.15
     чтоб
    1.13
     if
    1.13
     سپس
    1.09
    Activations Density 0.008%

    No Known Activations