© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 130844
    Prev
    Next
    INDEX
    Explanations

    The neuron fires strongly on header and metadata tokens—proper names, dates, bylines, and section labels.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    dates and numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     PUSTAKA
    -1.12
    nitř
    -1.09
    ceptable
    -1.07
     οποίο
    -1.06
     which
    -1.06
     деца
    -1.05
     eleva
    -1.03
    zość
    -1.02
     necesar
    -1.02
    onesi
    -1.02
    POSITIVE LOGITS
    ↵↵↵
    1.21
     redenen
    1.16
     oluyor
    1.15
     やすい
    1.11
     semplici
    1.08
    為に
    1.08
    /}
    1.07
     років
    1.04
    に入れる
    1.04
     चीज़
    1.03
    Activations Density 0.038%

    No Known Activations