© 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. 12423
    Prev
    Next
    INDEX
    Explanations

    our team/company/service

    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
     their
    -1.52
     while
    -1.34
     sejumlah
    -1.30
     it
    -1.28
     supuestamente
    -1.23
     those
    -1.22
    ihnachts
    -1.21
     necesitaba
    -1.20
    breviations
    -1.19
     teníamos
    -1.17
    POSITIVE LOGITS
     goal
    1.48
     aim
    1.41
     website
    1.34
     vider
    1.24
    ῳ
    1.22
     philosophy
    1.20
     database
    1.19
    澌
    1.16
    Latest
    1.16
     italia
    1.16
    Activations Density 0.036%

    No Known Activations