© 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. 39344
    Prev
    Next
    INDEX
    Explanations

    in followed by dimensions

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

    The neuron fires on numeric measurement expressions—numbers paired with units describing dimensions (e.g. “2.4 mm in depth,” “1.7 meters in height,” “319 kilometers in diameter”).

    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
    逦
    -1.74
    撂
    -1.71
    嗩
    -1.65
    岨
    -1.58
    玙
    -1.57
    开心
    -1.55
    Muchas
    -1.55
    陬
    -1.53
    RAG
    -1.52
    馋
    -1.52
    POSITIVE LOGITS
     which
    2.66
     has
    1.94
     if
    1.90
     although
    1.82
     at
    1.79
     with
    1.79
     since
    1.79
     when
    1.77
     who
    1.75
     whose
    1.71
    Activations Density 0.055%

    No Known Activations