© 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. 10-GEMMASCOPE-RES-131K
    4. 86788
    Prev
    Next
    INDEX
    Explanations

    indefinite article followed by noun

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

    The neuron selectively activates on numerical tokens—especially decimal numbers—i.e. it spotlights numeric values in the text.

    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
     from
    -1.65
     вернуться
    -1.53
    Външни
    -1.48
     inapropiados
    -1.41
     its
    -1.41
     воспользоваться
    -1.36
    ⅅ
    -1.34
     piccola
    -1.33
     открыть
    -1.26
     of
    -1.25
    POSITIVE LOGITS
    лів
    1.64
     некото
    1.63
    が違う
    1.58
     včetně
    1.55
     sorta
    1.51
    eventually
    1.48
     depois
    1.47
     різних
    1.46
     більше
    1.45
     luego
    1.40
    Activations Density 0.044%

    No Known Activations