© 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. 9750
    Prev
    Next
    INDEX
    Explanations

    new Promise or Response

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

    The neuron is highly sensitive to formal technical or specification language, especially occurrences of API names and related jargon.

    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
     श
    0.59
     McGregor
    0.56
    PayPal
    0.55
    anniksi
    0.55
     شا
    0.55
    anjing
    0.54
     Noyes
    0.54
     clearfix
    0.54
    鰍
    0.53
    crawler
    0.53
    POSITIVE LOGITS
    moz
    0.75
     Uint
    0.69
    Uint
    0.68
    CrossOrigin
    0.66
     moz
    0.61
     Blob
    0.59
     onload
    0.59
     crossorigin
    0.58
     worker
    0.57
     MSE
    0.57
    Activations Density 0.022%

    No Known Activations