© 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. 8866
    Prev
    Next
    INDEX
    Explanations

    c# code snippets

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

    The neuron fires on tokens that appear in software‐technical contexts—especially parts of file paths, URLs, and assembly-metadata strings.

    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
     tuve
    0.87
    iye
    0.84
     ragazza
    0.83
     মেয়ে
    0.79
    跏
    0.77
    orderDisplay
    0.76
     avevo
    0.76
     такую
    0.75
     healer
    0.74
    któ
    0.74
    POSITIVE LOGITS
    Thousands
    0.81
    En
    0.77
    Cargo
    0.75
    ]
    0.75
    在
    0.74
    Hunting
    0.73
    </
    0.73
    thousands
    0.72
    }&
    0.71
    &
    0.71
    Activations Density 0.000%

    No Known Activations