© 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. 34-GEMMASCOPE-RES-131K
    7. 49837
    Prev
    Next
    INDEX
    Explanations

    list of items

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

    The neuron strongly activates on numeric tokens that indicate list or category counts (e.g. the numbers next to “List of…” or “Category:” entries).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     several
    -0.94
    如
    -0.93
    दो
    -0.93
    BRARY
    -0.92
     Commentaires
    -0.90
    stoffen
    -0.90
     detergente
    -0.90
    值
    -0.89
     astonished
    -0.86
    ėjimas
    -0.86
    POSITIVE LOGITS
     list
    1.12
    有哪些
    1.06
    一覧
    1.04
     otras
    0.94
    階の
    0.92
     quizás
    0.91
     ganadores
    0.91
     Fifteen
    0.85
     menurut
    0.85
     teniendo
    0.85
    Activations Density 0.141%

    No Known Activations