© 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. 14370
    Prev
    Next
    INDEX
    Explanations

    package example

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

    The neuron activates on URL or filesystem‐style path segments (e.g. domain names, slashes, file paths).

    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
    Workspace
    0.71
    OptionPane
    0.70
     sirven
    0.70
     funcionan
    0.70
    Element
    0.68
    Unhandled
    0.68
     funcionar
    0.67
    ေ
    0.67
     internos
    0.67
    Config
    0.66
    POSITIVE LOGITS
    taining
    0.77
     هذا
    0.75
    avax
    0.70
     Роз
    0.70
    ée
    0.69
    myapplication
    0.69
     cognac
    0.69
    teenth
    0.68
     Dét
    0.68
    adays
    0.67
    Activations Density 0.000%

    No Known Activations