© 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. 5734
    Prev
    Next
    INDEX
    Explanations

    measure of, mint, dearly

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

    The neuron fires on numeric expressions (quantities, measurements, statistics, especially decimal‐formatted numbers) 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
    することができる
    1.16
    …………………………………………
    1.09
    证券投资基金
    1.08
    ________________
    1.06
    ================
    1.05
    ----------------
    1.05
    ることができる
    1.03
    ................
    1.02
    ################
    1.02
                                   
    0.99
    POSITIVE LOGITS
    ナトリ
    1.52
     acknow
    1.47
     അദ്ദേ
    1.47
     construc
    1.38
     ermög
    1.31
     accom
    1.28
     wellknown
    1.28
     manuf
    1.23
     andRow
    1.22
     combina
    1.20
    Activations Density 0.507%

    No Known Activations