© 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. 13045
    Prev
    Next
    INDEX
    Explanations

    start of sentence followed by verb

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron fires strongly on key content words—especially proper names and main action verbs—in narrative prose.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    din
    -0.90
    dn
    -0.89
     lalu
    -0.88
     them
    -0.88
    .[
    -0.87
     then
    -0.86
     its
    -0.85
     Международ
    -0.83
     ”
    -0.83
     Weltkrieg
    -0.81
    POSITIVE LOGITS
    bảng
    1.07
     můžete
    1.07
     dennoch
    1.05
     végétal
    1.03
    继续
    1.01
     prochaine
    1.00
     textu
    1.00
    bước
    0.99
     daarom
    0.97
     кстати
    0.97
    Activations Density 0.005%

    No Known Activations