© 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. 24-GEMMASCOPE-2-RES-16K
    7. 6101
    Prev
    Next
    INDEX
    Explanations

    preposition + noun/determiner

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

    This neuron primarily detects numeric tokens (especially numbers with digits or decimal points).

    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
    6
    0.61
    4
    0.53
    api
    0.52
    1
    0.52
    Â
    0.52
    economic
    0.51
    ю
    0.50
    athe
    0.50
     lung
    0.50
    ®
    0.49
    POSITIVE LOGITS
     coisas
    0.70
     Alguns
    0.69
     THAT
    0.66
     specialises
    0.65
    كيد
    0.65
     Algunos
    0.65
    ্ি
    0.65
     keltiradi
    0.65
     keeps
    0.64
     rezat
    0.64
    Activations Density 0.222%

    No Known Activations