© 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. 31-GEMMASCOPE-2-RES-16K
    7. 15943
    Prev
    Next
    INDEX
    Explanations

    file extension

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

    The neuron is keyed to technical security/malware terminology, especially ransomware-related words (e.g. names, encryption, data extension).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    mentions of computer files—especially filenames, extensions, formats, and operations on them like renaming, encoding, or appending extensions.

    oai_token-act-pair · gpt-5Triggered 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
    ложении
    0.58
    aporte
    0.50
    司令
    0.50
    軻
    0.49
    弟子
    0.48
    قتها
    0.48
     البريط
    0.47
    advers
    0.47
    .([]
    0.46
    Big
    0.46
    POSITIVE LOGITS
     extension
    1.75
     Extension
    1.59
    extension
    1.59
    Extension
    1.58
     extensions
    1.58
    后缀
    1.53
     "*.
    1.51
    getExtension
    1.51
     suffix
    1.48
     filenames
    1.46
    Activations Density 0.130%

    No Known Activations