© 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. 120023
    Prev
    Next
    INDEX
    Explanations

    phrases followed by short words

    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
     maler
    -1.30
     lørdag
    -1.28
     acest
    -1.27
    かしい
    -1.23
     și
    -1.17
     permite
    -1.17
     ”
    -1.16
     augustus
    -1.13
     solicita
    -1.13
    windowFixed
    -1.12
    POSITIVE LOGITS
    Since
    1.55
    Endereço
    1.41
    Throughout
    1.40
    símbolo
    1.39
    ㊗
    1.38
     олив
    1.36
    lıyor
    1.35
     haría
    1.34
     knew
    1.34
     prudent
    1.33
    Activations Density 0.031%

    No Known Activations