© 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. 377
    Prev
    Next
    INDEX
    Explanations

    This neuron is triggered by numeric tokens—dates, times, and other number-related expressions.

    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
     ہیں
    0.51
     ہوں
    0.51
    ]}
    0.50
    сера
    0.50
    िंट
    0.50
     voters
    0.50
    )}
    0.49
    ခဲ့
    0.49
     voter
    0.48
     dq
    0.48
    POSITIVE LOGITS
    ト
    0.59
    Soph
    0.55
    ANGE
    0.51
     GERM
    0.50
    သ
    0.50
    タン
    0.49
    ielleicht
    0.49
    ルー
    0.48
    Arsenal
    0.48
    abilidades
    0.48
    Activations Density 0.000%

    No Known Activations