© 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. 110897
    Prev
    Next
    INDEX
    Explanations

    endings of phrases

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

    The neuron fires on words that introduce or accompany numeric values or measurements (i.e. tokens tied to quantitative data).

    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
    pēc
    -1.71
    蓠
    -1.66
     kurios
    -1.59
     about
    -1.57
    莛
    -1.56
     yle
    -1.50
     eki
    -1.48
    </tfoot>
    -1.46
    柺
    -1.46
     renowned
    -1.45
    POSITIVE LOGITS
     is
    2.00
     has
    1.82
     had
    1.70
     Though
    1.65
     Although
    1.63
     Shortly
    1.60
     It
    1.59
     Despite
    1.58
     if
    1.54
     Unlike
    1.53
    Activations Density 0.167%

    No Known Activations