© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 9186
    Prev
    Next
    INDEX
    Explanations

    Chronarium Collective or California

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

    The neuron strongly activates on words bearing Latin‐derived adjective suffixes (especially “-ous” and similar endings).

    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
    Ε
    0.52
    EK
    0.51
     ஓர்
    0.51
    Е
    0.50
    Э
    0.50
    Кон
    0.50
    OD
    0.48
    ПА
    0.48
     під
    0.48
    U
    0.48
    POSITIVE LOGITS
     எனப்படும்
    0.50
    ர்களும்
    0.42
    icians
    0.41
    цію
    0.41
     maupun
    0.39
    螈
    0.39
     hennes
    0.39
    嫚
    0.38
    ुअल
    0.38
    বাদের
    0.38
    Activations Density 0.030%

    No Known Activations