© 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. 10574
    Prev
    Next
    INDEX
    Explanations

    money, investments, or specific items

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

    The neuron is primarily activating on determiners—especially the indefinite article “a” and related words like “other.”

    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
    тивным
    0.79
     pedestal
    0.77
    ﺨ
    0.76
    щением
    0.76
    THING
    0.75
     بەر
    0.75
     financier
    0.74
     NAND
    0.74
     terminus
    0.74
    ёв
    0.74
    POSITIVE LOGITS
    йної
    0.94
     marquées
    0.84
     rispondere
    0.82
    emple
    0.81
    𝑨
    0.79
    𝐴
    0.79
    nombre
    0.78
    nurse
    0.78
    urato
    0.77
     інші
    0.75
    Activations Density 0.000%

    No Known Activations