© 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. 8321
    Prev
    Next
    INDEX
    Explanations

    money amounts

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

    The neuron activates on numeric tokens and measurements (e.g. digits, decimal values, percentages, statistics) 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
     但
    0.82
    ㅢ
    0.80
    刺繍
    0.79
    एट
    0.75
     discernible
    0.73
     必ず
    0.73
    ᅴ
    0.73
    ેશન
    0.72
    なり
    0.72
    द्योग
    0.71
    POSITIVE LOGITS
    </strong>
    0.77
    </h1>
    0.75
    </h4>
    0.75
    tract
    0.67
    )}(\
    0.67
    steins
    0.66
    tak
    0.64
     aberta
    0.64
    </h2>
    0.63
    push
    0.63
    Activations Density 0.001%

    No Known Activations