© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 13645
    Prev
    Next
    INDEX
    Explanations

    Min

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

    The neuron is triggered by tokens containing the substring “min.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arranged
    0.61
     parallel
    0.55
    Arrange
    0.55
     సభ్య
    0.54
    burner
    0.54
     paralelo
    0.53
    センチ
    0.53
    겁
    0.52
    ENSIONS
    0.51
    Jos
    0.51
    POSITIVE LOGITS
     Min
    1.01
     min
    0.97
    nesota
    0.96
     मिन
    0.92
    MIN
    0.91
    Min
    0.84
     MIN
    0.81
     Minn
    0.81
    min
    0.80
    мум
    0.80
    Activations Density 0.233%

    No Known Activations