© 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. 34-GEMMASCOPE-RES-131K
    7. 81454
    Prev
    Next
    INDEX
    Explanations

    International card payment

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

    This neuron fires on uppercase or trademark‐style tokens—e.g. brand names, acronyms, and other all‐caps words.

    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
    addTab
    -0.79
    اگر
    -0.79
    话
    -0.78
    筵
    -0.77
     UDP
    -0.77
    MAX
    -0.77
    Không
    -0.75
     Hose
    -0.74
     UCC
    -0.74
    UDP
    -0.73
    POSITIVE LOGITS
    ヒール
    0.90
     kaart
    0.83
     Karten
    0.82
    USAL
    0.81
     fatos
    0.77
     tess
    0.73
    doubles
    0.73
    うれ
    0.72
    asters
    0.71
    therapy
    0.71
    Activations Density 0.007%

    No Known Activations