© 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. 10-GEMMASCOPE-RES-131K
    4. 71138
    Prev
    Next
    INDEX
    Explanations

    months and days

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

    The neuron activates on numeric tokens—both integers and decimal‐format numbers (e.g. years, measurements, scores).

    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
    獁
    -1.59
    最后由
    -1.57
     ドット
    -1.47
    をご覧ください
    -1.47
     Более
    -1.46
    ブログ村
    -1.41
     MATHEMAT
    -1.38
     diseñados
    -1.38
    蠖
    -1.35
     étab
    -1.34
    POSITIVE LOGITS
     –
    1.77
     Zwiebel
    1.40
    些
    1.37
     cbd
    1.34
     sekä
    1.32
    ”,
    1.30
     Отечественной
    1.29
     просто
    1.29
                   
    1.27
     ،
    1.26
    Activations Density 0.098%

    No Known Activations