© 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. 10837
    Prev
    Next
    INDEX
    Explanations

    questions about specific scenarios

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

    This neuron is essentially a positional counter—it activates progressively stronger for tokens that come later in a document or block.

    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
    וּ
    -1.55
     hitherto
    -1.27
     moneys
    -1.21
    暧
    -1.21
    ־ה
    -1.18
    ַּ
    -1.18
     vermag
    -1.16
    丹药
    -1.16
     πρ
    -1.15
     робота
    -1.15
    POSITIVE LOGITS
     your
    1.80
     you
    1.54
    めっちゃ
    1.43
    おわりに
    1.43
    んでる
    1.34
     analiza
    1.30
    Класс
    1.23
     به‌
    1.23
     sizin
    1.19
     ‌
    1.18
    Activations Density 0.062%

    No Known Activations