© 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. 10-GEMMASCOPE-RES-131K
    7. 7133
    Prev
    Next
    INDEX
    Explanations

    now [current state/action]

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

    The neuron fires on temporal markers indicating current states or ongoing actions (e.g. “now,” “currently,” “undergoing,” “conducting”).

    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
     Songtext
    -1.64
    ༷
    -1.53
    ༵
    -1.53
    凩
    -1.50
    だけでなく
    -1.49
    臵
    -1.45
    isering
    -1.45
    3
    -1.44
    淠
    -1.44
    である
    -1.41
    POSITIVE LOGITS
     There
    1.61
    当你
    1.52
     or
    1.52
    懨
    1.50
    ↵↵
    1.50
    优点
    1.41
     duyg
    1.39
    缺点
    1.36
    と呼ば
    1.34
     gått
    1.34
    Activations Density 0.029%

    No Known Activations