© 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. 80889
    Prev
    Next
    INDEX
    Explanations

    to be or have

    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
    厢
    -1.22
     نکنید
    -1.21
    [:,:,
    -1.21
     raiſ
    -1.17
     faſt
    -1.16
    -1.16
    的一声
    -1.15
     بيها
    -1.14
    っぱり
    -1.14
    娯
    -1.11
    POSITIVE LOGITS
     be
    5.06
     have
    3.28
     være
    2.45
     been
    2.03
     быть
    1.97
    have
    1.85
     être
    1.82
     mieć
    1.80
    être
    1.66
     być
    1.58
    Activations Density 0.081%

    No Known Activations