© 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. 11393
    Prev
    Next
    INDEX
    Explanations

    both or two

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

    This neuron detects occurrences of the word “both” (including its equivalents in different languages, e.g. Russian “оба” or Spanish “ambas”).

    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
     is
    -3.00
    蠖
    -2.95
     of
    -2.48
    我们的
    -2.47
     jedną
    -2.36
     if
    -2.13
    戆
    -2.13
    dáms
    -2.00
    臜
    -1.98
     siehe
    -1.96
    POSITIVE LOGITS
    n
    2.61
    餿
    2.27
    The
    2.19
    l
    2.14
     encompassed
    2.14
    there
    2.11
    甡
    2.02
     godk
    1.99
    v
    1.94
     skrevet
    1.91
    Activations Density 0.000%

    No Known Activations