© 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. 85556
    Prev
    Next
    INDEX
    Explanations

    purpose of, type of, ability of

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

    The neuron strongly activates on long, information‐dense, expository prose—especially formal business or academic text filled with common function words (“of,” “and,” “the”) and technical nouns.

    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
     it
    -2.38
     akku
    -1.88
    produksi
    -1.55
    好吃的
    -1.55
     功效
    -1.54
    際の
    -1.52
     we
    -1.49
     inaprop
    -1.48
     电脑
    -1.47
     Ξ
    -1.46
    POSITIVE LOGITS
     Auflösung
    1.59
    あなた
    1.54
    On
    1.43
    我已经
    1.42
    Is
    1.41
    ไม่
    1.40
    為什麼
    1.38
    人類
    1.38
    學習
    1.38
    После
    1.37
    Activations Density 0.012%

    No Known Activations