© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 77534
    Prev
    Next
    INDEX
    Explanations

    state of becoming

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

    The neuron activates on numeric expressions—years, percentages, and other number tokens.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     sirop
    -0.91
    会在
    -0.82
     arrancar
    -0.81
     zitten
    -0.81
     haga
    -0.81
     مؤرشف
    -0.80
     gehad
    -0.78
    品です
    -0.77
    lisle
    -0.77
     zullen
    -0.77
    POSITIVE LOGITS
     become
    7.13
     becomes
    6.44
     becoming
    6.38
     became
    6.38
     Become
    6.03
    become
    5.72
    Become
    5.69
     menjadi
    5.03
    Becoming
    5.00
     Becoming
    4.94
    Activations Density 0.434%

    No Known Activations