© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 7593
    Prev
    Next
    INDEX
    Explanations

    rate of change

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

    The neuron fires on tokens that represent numerical measures or metrics—especially words and numbers indicating rates or quantities (e.g. “pace,” “rate,” or digit sequences).

    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
    низ
    0.58
     multiplicity
    0.55
    ExposureTime
    0.54
    aund
    0.54
    ǎ
    0.54
     nghịch
    0.54
    OFFSET
    0.53
    lived
    0.52
     пони
    0.51
    低い
    0.50
    POSITIVE LOGITS
    বেশ
    0.62
    டுப
    0.55
     certa
    0.55
     resultContent
    0.55
    𓏧
    0.55
     colorido
    0.55
     prédio
    0.54
     impon
    0.54
     Nesse
    0.53
     کلاس
    0.53
    Activations Density 0.000%

    No Known Activations