© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 70735
    Prev
    Next
    INDEX
    Explanations

    disrupt or disturb

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

    disruption and disturbance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
     er
    0.54
     humiliation
    0.54
     stupidity
    0.52
     preclude
    0.51
     incompetence
    0.51
     it
    0.50
    ни
    0.49
     I
    0.49
     insuf
    0.49
     bane
    0.49
    POSITIVE LOGITS
    ganggu
    0.99
     Disturb
    0.96
     disturbances
    0.95
     disturbance
    0.94
     Disrupt
    0.89
     disrupt
    0.84
    バランス
    0.84
     disruptions
    0.83
     disturbed
    0.82
     disruption
    0.81
    Activations Density 0.079%

    No Known Activations