© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 13957
    Prev
    Next
    INDEX
    Explanations

    every single

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

    The neuron strongly activates on occurrences of the word “single,” especially in the phrase “every single ….”

    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
    所以我
    -2.17
     is
    -2.03
    ࿊
    -2.00
    でも
    -1.95
    ⦊
    -1.88
    ？”
    -1.79
     resposta
    -1.78
    ⢪
    -1.74
     certaines
    -1.74
    需求
    -1.70
    POSITIVE LOGITS
    there
    2.27
    ization
    2.09
    ischof
    2.05
    ゎ
    2.03
    vantaged
    1.98
    weetened
    1.98
    ﾏ
    1.97
    儅
    1.94
    ﾓ
    1.94
    している
    1.92
    Activations Density 0.002%

    No Known Activations