© 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-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-16K
    7. 9482
    Prev
    Next
    INDEX
    Explanations

    interrupt or disrupt

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    loadFile
    0.37
    栯
    0.37
    AssetDiscovery
    0.36
    EnableCOMDAT
    0.36
    follower
    0.34
    DialogWhenLarge
    0.34
    EFF
    0.34
     ગયો
    0.34
    従
    0.34
     THRO
    0.33
    POSITIVE LOGITS
     interrupt
    2.81
     interrupted
    2.70
     interruption
    2.66
     Interrupt
    2.66
     interrupting
    2.64
    Interrupt
    2.59
     interruptions
    2.59
     interrupts
    2.59
    interrupt
    2.58
     interrump
    2.45
    Activations Density 0.179%

    No Known Activations