© 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. 8377
    Prev
    Next
    INDEX
    Explanations

    start of code or commands

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

    This neuron lights up on unusual or rare tokens—especially capitalized or otherwise infrequent 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
    刬
    0.76
     gyárt
    0.75
    というか
    0.73
     werewolf
    0.73
     sarcoma
    0.72
     பட்
    0.71
     ສຳ
    0.71
     پدر
    0.68
     เซ
    0.68
     ขั้น
    0.67
    POSITIVE LOGITS
    не
    0.96
    on
    0.89
    те
    0.79
    
    0.77
     termed
    0.76
    am
    0.74
    с
    0.73
     necessitated
    0.72
    ার
    0.71
    ни
    0.71
    Activations Density 0.000%

    No Known Activations