© 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. 3801
    Prev
    Next
    INDEX
    Explanations

    product and its features

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

    The neuron primarily fires on the word “product” (and its variants or headings, including plurals and other-language forms).

    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
    ."
    -2.83
    ="
    -2.47
     /
    -2.16
    at
    -2.06
    msford
    -1.98
    ):
    -1.93
     Your
    -1.91
    ↵
    -1.87
     rushing
    -1.87
     =
    -1.86
    POSITIVE LOGITS
     cotidiano
    2.56
     unangemess
    2.45
     メニュー
    2.41
     protegido
    2.34
     pintado
    2.23
     sorgfäl
    2.22
     ausdrück
    2.22
     cruzado
    2.19
     beneficiario
    2.17
     inesperado
    2.16
    Activations Density 0.002%

    No Known Activations