© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 111286
    Prev
    Next
    INDEX
    Explanations

    conjunctions introducing context

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

    The neuron flags numeric expressions—especially standalone numbers, percentages, and decimal values—wherever they appear in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     to
    -1.57
     especially
    -1.30
    creenshot
    -1.23
    PointerException
    -1.22
     particularly
    -1.21
     Herausforderung
    -1.18
    lossenen
    -1.16
     when
    -1.16
     however
    -1.15
     Aufführung
    -1.14
    POSITIVE LOGITS
    nede
    1.19
     exerts
    1.19
     denkt
    1.15
    别的
    1.13
     Medications
    1.12
    enciaga
    1.11
     دریافت‌شده
    1.09
    زاده
    1.06
     еще
    1.05
    
    1.05
    Activations Density 0.069%

    No Known Activations