© 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. 10152
    Prev
    Next
    INDEX
    Explanations

    java import statements

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

    This neuron detects the abbreviations “ed” or “eds” (and similar citation markers) in bibliographic reference lists.

    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
    <
    0.56
    left
    0.50
     شده‌است
    0.49
    English
    0.49
    のに
    0.49
    len
    0.48
    banana
    0.48
    jetbrains
    0.48
    lena
    0.48
    ướng
    0.48
    POSITIVE LOGITS
     alleviated
    0.63
    晎
    0.61
    ↵↵↵↵↵↵↵↵↵
    0.60
    ↵↵↵↵↵↵↵↵↵↵
    0.60
     principalement
    0.60
    ર્ડ
    0.60
     semblables
    0.58
    ↵↵↵↵↵↵↵↵↵↵↵
    0.58
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.58
     кле
    0.57
    Activations Density 0.003%

    No Known Activations