© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 8653
    Prev
    Next
    INDEX
    Explanations

    part of

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

    This neuron detects occurrences of the common “part of the” phrase (i.e. the “part of the” sequence of function words).

    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
     เมตร
    1.16
     وعلى
    1.13
    approximately
    1.08
    OM
    1.05
    "),
    1.02
     davanti
    0.98
     seguida
    0.96
    𝗘
    0.96
     suficient
    0.96
    ")
    0.95
    POSITIVE LOGITS
    ীদার
    1.58
    ীদ
    1.22
    ت
    1.18
    ح
    1.13
    ুর
    1.10
    зь
    1.09
    тории
    1.09
    ică
    1.05
    とめ
    1.05
    лу
    1.05
    Activations Density 0.099%

    No Known Activations