© 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. 34-GEMMASCOPE-RES-131K
    7. 2278
    Prev
    Next
    INDEX
    Explanations

    get followed by a specific noun

    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_34/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
    achusetts
    -1.10
     envoie
    -1.08
    ᓚ
    -1.07
     Meksi
    -1.06
     Meksiko
    -1.05
    takt
    -1.03
     exé
    -1.03
     ijs
    -1.03
    。"
    -1.02
    ageable
    -1.02
    POSITIVE LOGITS
    ,
    1.02
     invert
    0.93
     very
    0.90
     principally
    0.89
     generalmente
    0.89
    רים
    0.89
     aptly
    0.88
    金曜
    0.88
     illustrate
    0.87
     &
    0.86
    Activations Density 0.011%

    No Known Activations