© 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. 70374
    Prev
    Next
    INDEX
    Explanations

    months ago or later

    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
     andererseits
    -1.41
     Bedürfn
    -1.40
     heut
    -1.37
     algumas
    -1.33
    ített
    -1.33
     sabid
    -1.32
    ('
    -1.32
    不同的
    -1.31
     гораздо
    -1.30
     spéciaux
    -1.29
    POSITIVE LOGITS
     months
    1.73
    months
    1.66
     maanden
    1.46
     çik
    1.38
    蚍
    1.37
     $_[
    1.35
     mesi
    1.30
    半年
    1.30
    Months
    1.28
     месяца
    1.28
    Activations Density 0.040%

    No Known Activations