© 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. 31-GEMMASCOPE-2-RES-16K
    7. 7151
    Prev
    Next
    INDEX
    Explanations

    since year, BERT

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

    The neuron is chiefly triggered by numeric tokens, proper‐name tokens, and acronyms—i.e. numbers and named entities (like “Justice,” “5G,” “CBS,” etc.).

    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_31_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
    🩶
    1.12
    🫡
    1.09
    🫤
    1.03
    🥹
    0.98
    🫠
    0.95
    🫢
    0.91
    🫂
    0.91
    🫶
    0.91
    🫣
    0.90
    🫰
    0.89
    POSITIVE LOGITS
     ২০১৯
    1.50
     coronavirus
    1.48
    Coronavirus
    1.46
     Coronavirus
    1.44
     ২০২০
    1.39
    coronavirus
    1.27
     कोरोनावायरस
    1.04
     코로나
    1.04
     коронави
    0.99
     করোনাভাই
    0.98
    Activations Density 0.272%

    No Known Activations