© 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. 119608
    Prev
    Next
    INDEX
    Explanations

    year and period references

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

    The neuron fires on numeric tokens, i.e. any standalone numbers (including those with decimals).

    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
     アンド
    -1.58
     scoprire
    -1.40
     laim
    -1.38
    kách
    -1.37
     フレ
    -1.37
    痦
    -1.36
     vnt
    -1.36
     bont
    -1.35
    ắn
    -1.35
    龘
    -1.34
    POSITIVE LOGITS
    '
    1.55
     животных
    1.40
     "
    1.33
    1
    1.33
     jardín
    1.26
     araña
    1.24
    (
    1.21
    3
    1.20
     всичко
    1.19
    "
    1.19
    Activations Density 0.006%

    No Known Activations