© 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. 22-GEMMASCOPE-RES-131K
    7. 28583
    Prev
    Next
    INDEX
    Explanations

    hand reaching out or in

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

    The neuron fires on numeric tokens (especially decimal or integer values), i.e. it detects numbers in the text.

    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
    这种
    -1.07
     لكل
    -1.04
     utilizz
    -0.93
     trách
    -0.88
     iLocal
    -0.88
    maler
    -0.87
     MacLeod
    -0.86
    蔭
    -0.86
    zepte
    -0.85
     esprits
    -0.85
    POSITIVE LOGITS
    リューション
    0.97
     grasping
    0.94
    offerta
    0.94
    ᾷ
    0.92
    ToRefresh
    0.91
    好きです
    0.90
     touching
    0.89
    ࿚
    0.88
    částí
    0.86
     underneath
    0.86
    Activations Density 0.019%

    No Known Activations