© 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. 117
    Prev
    Next
    INDEX
    Explanations

    The neuron consistently fires on numeric expressions—both digits and spelled-out numbers (including ordinals and cardinals).

    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
     vadanti
    0.47
     vergleich
    0.45
     milliers
    0.43
     milhares
    0.43
     getUsersBy
    0.42
    😠
    0.41
     Prozent
    0.41
    🍘
    0.41
    🔬
    0.40
     genauso
    0.40
    POSITIVE LOGITS
     sided
    0.49
     दिवसीय
    0.45
     सदस्यीय
    0.43
    sided
    0.42
    idential
    0.41
    ided
    0.39
     dimensional
    0.38
     curved
    0.38
    -
    0.37
    рованная
    0.37
    Activations Density 0.000%

    No Known Activations