© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 67591
    Prev
    Next
    INDEX
    Explanations

    EFI, Brant, Brock, Sneaked

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

    The neuron strongly responds to occurrences of the “EFI”/“UEFI” acronym (i.e. references to EFI or UEFI).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    L
    -3.23
    \
    -3.22
    B
    -3.00
     '
    -2.95
    J
    -2.83
    E
    -2.78
     t
    -2.77
     It
    -2.67
    V
    -2.58
     has
    -2.56
    POSITIVE LOGITS
     parachoque
    3.70
     放題
    3.45
     起毛
    3.27
    鹮
    3.20
    ＊＊＊
    3.17
     広場
    3.16
    鱨
    3.14
     우리
    3.02
     vnnd
    2.98
     heo
    2.97
    Activations Density 0.010%

    No Known Activations