© 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. 34-GEMMASCOPE-RES-131K
    7. 76046
    Prev
    Next
    INDEX
    Explanations

    said they want

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

    This neuron detects quantitative data mentions—numerals, percentages, and other statistical figures.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     magari
    -0.98
     особли
    -0.97
     nini
    -0.95
    Especially
    -0.94
     thousands
    -0.91
    หลาย
    -0.90
     zul
    -0.89
    许多
    -0.89
    :{
    -0.86
    ◻
    -0.86
    POSITIVE LOGITS
     their
    2.02
     they
    1.52
     overall
    1.45
     or
    1.39
     compared
    1.38
     respondents
    1.27
     mereka
    1.26
     either
    1.25
     currently
    1.24
     demnach
    1.17
    Activations Density 0.072%

    No Known Activations