© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 2782
    Prev
    Next
    INDEX
    Explanations

    The neuron detects mentions of data storage and backup hardware (e.g. external drives, RAID setups, storage devices).

    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
    蟀
    0.61
    🐸
    0.61
     تیر
    0.57
     chibi
    0.56
    爐
    0.55
    езде
    0.55
    ध्ये
    0.53
    ApiKey
    0.53
    kfollowers
    0.53
    炉
    0.53
    POSITIVE LOGITS
     disk
    1.61
     Disk
    1.60
    disk
    1.52
    磁盘
    1.50
     disks
    1.49
    Disk
    1.49
     NTFS
    1.41
    硬盘
    1.41
     storage
    1.38
     Storage
    1.37
    Activations Density 0.501%

    No Known Activations