© 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. 8477
    Prev
    Next
    INDEX
    Explanations

    numbers and roles

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

    The neuron flags words acting as modifiers—i.e. adjectives or noun-prefix parts in compounds (like “operating” in “operating system,” “second” in “and second base,” “single-layer,” “Multi-plan,” “incomplete,” “lifestyle,” 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_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
    恣
    0.82
    リューション
    0.77
    वेदन
    0.77
    দর্শক
    0.73
    ሽን
    0.72
     Yatha
    0.71
    उद्योग
    0.71
     Usuarios
    0.71
    ógica
    0.70
     ไฟล์
    0.70
    POSITIVE LOGITS
     trois
    0.80
    ٣
    0.79
    鐵
    0.77
    為主
    0.75
    compatible
    0.74
     classe
    0.71
    /?
    0.71
    eer
    0.70
     pour
    0.68
    ligt
    0.68
    Activations Density 0.000%

    No Known Activations