© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 55667
    Prev
    Next
    INDEX
    Explanations

    car accident insurance claims

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

    The neuron fires strongly on phrasing that describes leaving or failing to report at an accident scene (i.e. hit-and-run contexts).

    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
     Metroid
    -1.05
     innumer
    -0.89
    锯
    -0.85
    execution
    -0.84
     plancha
    -0.83
     ((*
    -0.83
     différences
    -0.83
    Execution
    -0.82
     groen
    -0.82
     groet
    -0.82
    POSITIVE LOGITS
     insurance
    1.91
     collision
    1.58
     Insurance
    1.52
     injuries
    1.52
    insurance
    1.38
    Collision
    1.37
     crash
    1.35
     accident
    1.35
     collisions
    1.35
     injury
    1.34
    Activations Density 0.021%

    No Known Activations