© 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. 9771
    Prev
    Next
    INDEX
    Explanations

    word endings or abbreviations

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

    The neuron responds to short, two-letter letter sequences (bigrams) embedded within longer tokens.

    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
     and
    -2.25
     or
    -1.82
    縂
    -1.78
    鋮
    -1.69
    ↵
    -1.68
    就好了
    -1.60
     також
    -1.58
     citado
    -1.56
     belangrij
    -1.51
    Важно
    -1.51
    POSITIVE LOGITS
    hline
    1.82
    1.77
     bén
    1.73
     Represents
    1.73
     momentous
    1.72
    anova
    1.71
    鲞
    1.69
    eció
    1.67
    DISCLAIMER
    1.67
     magnificent
    1.67
    Activations Density 0.119%

    No Known Activations