© 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. 8290
    Prev
    Next
    INDEX
    Explanations

    pronoun reference and grammar rules

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

    The neuron specifically detects floating‐point numbers (numeric tokens containing a decimal point).

    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
    選舉
    0.92
    閉店
    0.78
     étroites
    0.78
    ू
    0.76
    曆
    0.74
    過程中
    0.74
    硼
    0.73
    ى
    0.73
    选举
    0.70
     draining
    0.69
    POSITIVE LOGITS
    s
    0.98
    вает
    0.84
    ﺸ
    0.79
     внутрен
    0.79
    klasse
    0.79
    themem
    0.76
    ের
    0.75
    우스
    0.75
    rova
    0.74
    soci
    0.74
    Activations Density 0.000%

    No Known Activations