© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 65856
    Prev
    Next
    INDEX
    Explanations

    words starting with "boot"

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

    The neuron fires on any occurrence of the substring “boot” (e.g. in “bootcamp,” “bootstrap,” “boot file,” etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    轮胎
    -1.02
    hydrogen
    -0.85
    结语
    -0.83
    包围
    -0.82
    human
    -0.81
    izacion
    -0.80
    聞き
    -0.78
    窗户
    -0.78
    自転車
    -0.77
    过头
    -0.77
    POSITIVE LOGITS
    camp
    1.33
     boot
    1.27
     Boot
    1.18
    boot
    1.13
     camp
    1.06
    laces
    1.04
    Boot
    1.02
    ontale
    1.00
     booting
    0.99
    legged
    0.97
    Activations Density 0.010%

    No Known Activations