© 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. 22-GEMMASCOPE-RES-131K
    7. 75000
    Prev
    Next
    INDEX
    Explanations

    currently

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

    The neuron specializes in spotting magnitude or quantity words—especially superlatives and strong numeric or comparative terms (e.g. “largest,” “greatest,” “many,” “one of”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     siempre
    -1.54
     hereafter
    -1.49
     always
    -1.43
     henceforth
    -1.43
     eventually
    -1.37
     subsequently
    -1.35
     всегда
    -1.31
     first
    -1.30
     vždy
    -1.29
    以後
    -1.23
    POSITIVE LOGITS
     đang
    1.55
     currently
    1.52
    currently
    1.42
    Currently
    1.41
     sedang
    1.38
    current
    1.25
     current
    1.22
     about
    1.20
    正在
    1.18
     Current
    1.14
    Activations Density 0.094%

    No Known Activations