© 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. 59227
    Prev
    Next
    INDEX
    Explanations

    students learn and participate

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

    The neuron is keyed to detect numeric information—counts, ages, durations, or other statistics—where numbers or quantifiers appear 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_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
    ございません
    -0.95
     simplemente
    -0.93
     Teach
    -0.90
    ないです
    -0.89
     teaching
    -0.89
    āci
    -0.89
    furl
    -0.87
     Teaching
    -0.87
    teach
    -0.87
    ให้
    -0.85
    POSITIVE LOGITS
     learn
    1.98
     participate
    1.61
     receive
    1.59
     learns
    1.46
     learning
    1.45
    Learn
    1.41
     receives
    1.38
    learn
    1.36
     spend
    1.35
     Receive
    1.29
    Activations Density 0.052%

    No Known Activations