© 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. 103919
    Prev
    Next
    INDEX
    Explanations

    listing items

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

    The neuron detects standalone numerals used as section or step/example headings (i.e. list or example numbers).

    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
     a
    -1.81
     and
    -1.68
    menü
    -1.58
     the
    -1.57
     españ
    -1.55
     чёр
    -1.54
     Pued
    -1.53
     هار
    -1.53
     behulp
    -1.52
    桖
    -1.52
    POSITIVE LOGITS
    :
    2.56
     That
    1.68
    2
    1.64
    That
    1.54
    0
    1.51
     incluso
    1.48
    !!!!
    1.45
    是否
    1.44
           
    1.42
    5
    1.42
    Activations Density 0.054%

    No Known Activations