© 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. 13638
    Prev
    Next
    INDEX
    Explanations

    programming language constructs

    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
    athered
    -1.21
     różnych
    -1.20
    rfan
    -1.18
     判断
    -1.18
    ridescent
    -1.16
    aried
    -1.16
     instalação
    -1.14
    媗
    -1.11
     trois
    -1.10
     gebruiken
    -1.09
    POSITIVE LOGITS
     ()=>
    1.20
     you
    1.10
    Just
    1.09
     atau
    1.09
     because
    1.09
     or
    1.08
     after
    1.08
    although
    1.05
    rored
    1.03
     discernible
    1.03
    Activations Density 0.008%

    No Known Activations