© 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. 24-GEMMASCOPE-2-RES-16K
    7. 6287
    Prev
    Next
    INDEX
    Explanations

    communications and hardware protocols

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

    The main thing this neuron does is detect technical numeric and alphanumeric identifiers—like model numbers, measurement values, and protocol codes—in specification‐style text.

    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
     কষ্টে
    0.79
    ماع
    0.74
    社會
    0.73
    地理
    0.73
    幔
    0.73
     காற்றின்
    0.73
    歌
    0.71
    犁
    0.71
    農
    0.70
    地点
    0.70
    POSITIVE LOGITS
     circuitry
    1.28
     USB
    1.23
     voltage
    1.20
     ports
    1.20
    电源
    1.20
    🔌
    1.20
     HDMI
    1.19
     wiring
    1.18
     Ethernet
    1.18
    电路
    1.15
    Activations Density 0.531%

    No Known Activations