© 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. 60888
    Prev
    Next
    INDEX
    Explanations

    programming construct "with"

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

    The neuron primarily activates on occurrences of the word “with.”

    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
    茕
    -2.06
    撄
    -1.94
    "",
    -1.91
    鲞
    -1.88
    盉
    -1.88
    觧
    -1.87
     they
    -1.86
    ſſen
    -1.83
    戗
    -1.82
    ſſel
    -1.81
    POSITIVE LOGITS
     However
    2.25
     Anyone
    2.05
     Therefore
    2.03
     Hundreds
    2.00
     "$
    1.99
    </sup>
    1.95
    It
    1.95
     Those
    1.93
    s
    1.92
    ésil
    1.91
    Activations Density 0.012%

    No Known Activations