© 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. 10-GEMMASCOPE-RES-131K
    7. 42330
    Prev
    Next
    INDEX
    Explanations

    verb followed by preposition/auxiliary

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

    The neuron fires on named entities—proper names (people, places, organizations) and other title-cased or otherwise “special” tokens (e.g. specific names, dates, roles).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    ַּ
    -2.00
    ִּ
    -1.73
    ּוֹ
    -1.73
     its
    -1.70
     with
    -1.66
     over
    -1.56
    niña
    -1.54
     without
    -1.53
     nuanced
    -1.46
     on
    -1.45
    POSITIVE LOGITS
    狠狠
    1.73
     النبات
    1.55
     pittores
    1.49
    ׇ
    1.42
     nød
    1.41
     chré
    1.41
     /**
    1.40
     herbes
    1.40
    Ꭵ
    1.39
     دارند
    1.38
    Activations Density 0.079%

    No Known Activations