© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 6021
    Prev
    Next
    INDEX
    Explanations

    list names or types

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

    This neuron detects numeric tokens—especially decimal numbers or measurements—embedded in the text.

    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_24_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
     set
    0.71
    REDIR
    0.66
    টসম্যান
    0.66
    គាត់
    0.66
    ৬৫
    0.66
    歳
    0.66
     unaccompanied
    0.65
    ់
    0.65
     состоя
    0.64
     поезд
    0.64
    POSITIVE LOGITS
     antiguos
    0.80
    ahah
    0.79
    다른
    0.78
     asesin
    0.76
     actualizado
    0.74
    ान
    0.73
     eigene
    0.73
     화면
    0.73
     simulations
    0.72
    仿真
    0.72
    Activations Density 0.002%

    No Known Activations