© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 98544
    Prev
    Next
    INDEX
    Explanations

    year, day, month, week

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

    The neuron fires on numeric tokens (including years, days, months, and decimal values).

    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
    UCIÓN
    -1.65
    を
    -1.59
    そして
    -1.51
    は
    -1.47
    <bos>
    -1.44
     also
    -1.41
    と
    -1.40
    がある
    -1.30
    かと
    -1.30
    匿名使用者
    -1.27
    POSITIVE LOGITS
    為に
    1.52
    んですよね
    1.45
    つづく
    1.45
    様な
    1.41
    になれば
    1.39
     manquante
    1.38
    あー
    1.32
     wzglę
    1.30
    になったら
    1.30
    に似
    1.28
    Activations Density 0.038%

    No Known Activations