© 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. 24-GEMMASCOPE-2-RES-16K
    7. 9581
    Prev
    Next
    INDEX
    Explanations

    column or data differences

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

    The neuron specifically activates on numeric tokens (especially decimal numbers).

    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
    8
    0.85
    ាល់
    0.83
    ता
    0.78
    ۸
    0.78
    9
    0.77
    öm
    0.76
    ation
    0.75
    aih
    0.75
    annya
    0.71
    ੰ
    0.71
    POSITIVE LOGITS
    联邦
    0.88
    五个
    0.84
    强势
    0.83
    缅
    0.78
     peningkatan
    0.77
    一些
    0.76
    🆗
    0.76
    echolog
    0.75
     Highlanders
    0.75
     personaje
    0.74
    Activations Density 0.001%

    No Known Activations