© 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
    2. Gemma-3-12B
    3. 31-GEMMASCOPE-2-RES-16K
    4. 10671
    Prev
    Next
    INDEX
    Explanations

    bootup, bootable, bootloaders, boot times

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

    The neuron detects mentions of “boot” (and boot-related forms like bootstrap, bootable, boot time, etc.).

    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
    訂
    0.64
    rocyte
    0.64
     emeritus
    0.64
    subheader
    0.60
    ```
    0.59
    scanf
    0.58
     Emeritus
    0.57
     setTimeout
    0.56
    Samsung
    0.56
     subjunctive
    0.55
    POSITIVE LOGITS
     Boot
    0.71
    朶
    0.60
     booted
    0.60
     গ্র
    0.59
     ブーツ
    0.59
     boot
    0.59
     সক্ষম
    0.56
    Boot
    0.55
     ঘু
    0.55
     Boots
    0.55
    Activations Density 0.029%

    No Known Activations