© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 129659
    Prev
    Next
    INDEX
    Explanations

    The neuron detects mentions of vehicular accidents or crashes.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    vehicle crash, accident, collide

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     to
    -1.76
    /
    -1.20
    mıştır
    -1.20
    ithin
    -1.18
     for
    -1.10
    +
    -1.09
    ],'
    -1.09
    extends
    -1.08
     līdz
    -1.08
     ۲۰۰
    -1.07
    POSITIVE LOGITS
    ῖς
    1.34
     Thursday
    1.19
    şağı
    1.15
     caused
    1.14
    簡單
    1.13
    襪
    1.11
    ὺς
    1.11
     two
    1.07
     emosi
    1.05
     collide
    1.05
    Activations Density 0.030%

    No Known Activations