© 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. 79749
    Prev
    Next
    INDEX
    Explanations

    initials or abbreviations followed by punctuation

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

    This neuron detects single-letter uppercase author initials (e.g. J, M, D) in scholarly citation entries.

    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
     either
    -1.35
     творо
    -1.27
     until
    -1.26
     by
    -1.23
     of
    -1.11
    即購入
    -1.10
     that
    -1.10
     different
    -1.09
     to
    -1.09
    よろしくお願い
    -1.05
    POSITIVE LOGITS
     and
    1.86
    และ
    1.29
     และ
    1.18
     métallique
    1.16
    giá
    1.13
     Allows
    1.11
     réglable
    1.08
     danske
    1.06
     rembour
    1.05
     Arkivert
    1.04
    Activations Density 0.004%

    No Known Activations