© 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. 34-GEMMASCOPE-RES-131K
    7. 117550
    Prev
    Next
    INDEX
    Explanations

    disk partition and boot system

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

    The neuron detects mentions of disk partition operations (e.g., resizing, creating, deleting, or expanding partitions).

    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
    ֮
    -0.80
    alignSelf
    -0.79
     discussed
    -0.77
    InsertCommand
    -0.75
     réglementation
    -0.75
    plaatst
    -0.75
    楼梯
    -0.74
    posx
    -0.73
     sustent
    -0.72
     güçlü
    -0.71
    POSITIVE LOGITS
     partition
    1.70
    partition
    1.43
    Partition
    1.26
     partitions
    1.25
    boot
    1.14
    SYSTEM
    1.13
    system
    1.08
    Drive
    1.05
     SYSTEM
    1.05
    System
    1.05
    Activations Density 0.060%

    No Known Activations