© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 118788
    Prev
    Next
    INDEX
    Explanations

    collision and crash events

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

    The neuron fires on terms describing vehicle collisions or crashes.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    ⋁
    -0.78
     отношение
    -0.75
    Killing
    -0.71
    delà
    -0.69
     informieren
    -0.69
    componentes
    -0.69
    姍
    -0.68
     traces
    -0.67
    membrance
    -0.66
     отношениях
    -0.66
    POSITIVE LOGITS
     collision
    4.41
     collisions
    3.84
    collision
    3.45
    Collision
    3.38
     Collision
    3.34
     collide
    3.02
     collided
    2.75
     colliding
    2.69
    COLL
    2.39
    collide
    2.39
    Activations Density 0.038%

    No Known Activations