© 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. 5357
    Prev
    Next
    INDEX
    Explanations

    device drivers

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

    The neuron is picking up on technical alphanumeric identifiers—especially version numbers, hex addresses, port codes, and other uppercase-heavy numeric strings.

    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
    htaccess
    0.64
    maketitle
    0.63
    餐廳
    0.57
     CDN
    0.55
     memorials
    0.55
    民宿
    0.55
    mongo
    0.54
    🍛
    0.54
    ovies
    0.53
     whitew
    0.53
    POSITIVE LOGITS
     usb
    1.45
     USB
    1.44
    USB
    1.42
    usb
    1.38
    Usb
    1.30
     device
    1.24
     Device
    1.19
    デバイス
    1.17
    device
    1.14
     driver
    1.13
    Activations Density 0.258%

    No Known Activations