© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 15683
    Prev
    Next
    INDEX
    Explanations

    consecutive occurrences or periods

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

    The neuron detects occurrences of the word “consecutive,” as in phrases like “seventh consecutive year” or “sixth consecutive loss.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    に来て
    -2.38
    {
    -2.22
    に行く
    -2.17
    蠖
    -2.09
    に行って
    -1.87
    apparently
    -1.83
    敺
    -1.80
    皷
    -1.79
    </strong>
    -1.76
    分からない
    -1.69
    POSITIVE LOGITS
    ～～
    2.41
    ～～～
    2.22
    ～～～～
    2.11
    縯
    2.00
    ”、“
    2.00
    ～　
    1.96
    CHREIBUNG
    1.94
    n
    1.93
    　↓
    1.88
    ୌ
    1.87
    Activations Density 0.012%

    No Known Activations