© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 13593
    Prev
    Next
    INDEX
    Explanations

    led to

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

    The neuron looks for the past‐tense verb “led,” especially in phrases like “has led to.”

    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
    such
    -1.88
     such
    -1.60
     is
    -1.48
     gratuito
    -1.46
    ,;
    -1.40
     Such
    -1.37
    だったが
    -1.27
     Bereich
    -1.27
    .^
    -1.26
    原标题
    -1.25
    POSITIVE LOGITS
     you
    2.38
    䴀
    1.77
     by
    1.72
     OGSÅ
    1.56
     Kedua
    1.55
    Why
    1.48
    還會
    1.48
    也會
    1.41
    んの
    1.41
    Have
    1.41
    Activations Density 0.027%

    No Known Activations