© 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. 75239
    Prev
    Next
    INDEX
    Explanations

    timed events and intervals

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

    The neuron strongly activates on past‐tense verb forms (e.g. words ending in “-ed” or irregular past tense like “dreamt”).

    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
    -5.56
    ا
    -4.16
    e
    -3.55
     {
    -3.16
    ה
    -3.03
    1
    -2.80
     was
    -2.75
    鉏
    -2.42
    _{
    -2.41
     minim
    -2.39
    POSITIVE LOGITS
    関する
    2.91
     predomin
    2.64
    leggio
    2.59
    悒
    2.58
    谵
    2.55
    変わり
    2.45
    Skocz
    2.38
    ？！
    2.34
    对不起
    2.31
    
    2.28
    Activations Density 0.017%

    No Known Activations