© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 8634
    Prev
    Next
    INDEX
    Explanations

    Spring framework technologies

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

    The neuron fires on occurrences of the word “Spring” (as in the Spring Framework and related Spring technologies).

    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
     पंतप्रधान
    0.59
     choque
    0.59
     FXR
    0.59
     NICE
    0.59
     XGB
    0.57
     livraison
    0.55
     pô
    0.55
     ⭐
    0.55
     escul
    0.55
     desag
    0.55
    POSITIVE LOGITS
     widths
    0.50
    antees
    0.50
    тья
    0.49
    ImageQueue
    0.49
    只能
    0.47
     WIDTH
    0.47
    র্কের
    0.47
    ガ
    0.47
    getic
    0.47
    ColorBit
    0.47
    Activations Density 0.001%

    No Known Activations