© 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. 90899
    Prev
    Next
    INDEX
    Explanations

    balance between opposites

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

    The neuron fires on the coordinating conjunction “and.”

    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
     The
    -1.92
    </strong>
    -1.82
     ‘
    -1.70
     you
    -1.60
    â
    -1.58
     utilizando
    -1.57
    toDouble
    -1.54
     dando
    -1.50
    niająca
    -1.50
     â
    -1.48
    POSITIVE LOGITS
    ㆆ
    1.54
    糶
    1.51
     almak
    1.48
    ửi
    1.45
     bygger
    1.44
     this
    1.42
     legislat
    1.42
     skriva
    1.41
     土産
    1.41
     Rasulullah
    1.41
    Activations Density 0.072%

    No Known Activations