© 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. 98687
    Prev
    Next
    INDEX
    Explanations

    be or BE abbreviations

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

    The neuron responds strongly to the character sequence “be,” i.e. it detects tokens containing the bigram “be,” especially as a “Be”-prefix.

    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
    AutoresizingMask
    -2.78
    ad
    -2.38
    螃
    -2.30
    婠
    -2.30
    את
    -2.28
    an
    -2.27
    acterium
    -2.27
    "
    -2.22
    渽
    -2.19
     și
    -2.16
    POSITIVE LOGITS
     However
    2.64
     éstas
    2.56
     But
    2.55
     quizá
    2.55
     únicamente
    2.41
    During
    2.39
     obtend
    2.39
    9
    2.38
     Однако
    2.36
     anderer
    2.34
    Activations Density 0.033%

    No Known Activations