© 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. 7855
    Prev
    Next
    INDEX
    Explanations

    later or latter

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

    The neuron mainly activates on occurrences of the word “later.”

    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
     ܗܘ
    0.61
    立体
    0.57
    ligi
    0.57
     namely
    0.54
    ക്കുന്ന
    0.54
     ligands
    0.54
    骢
    0.50
    かれる
    0.50
     juntas
    0.48
     వ్యక్
    0.48
    POSITIVE LOGITS
     তারিখ
    0.76
    mark
    0.61
    pmap
    0.61
     titel
    0.60
    åd
    0.59
    Noir
    0.59
    å
    0.59
     instill
    0.58
    🕓
    0.58
    🕜
    0.57
    Activations Density 0.001%

    No Known Activations