© 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. 4240
    Prev
    Next
    INDEX
    Explanations

    accident investigation

    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_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
     tark
    -0.76
    setView
    -0.75
    器官
    -0.71
    inyl
    -0.70
     ingreso
    -0.69
     kell
    -0.69
    如有
    -0.68
    駛
    -0.68
     desafío
    -0.68
     Turismo
    -0.68
    POSITIVE LOGITS
     accident
    1.68
     Accident
    1.52
    Accident
    1.50
     investigators
    1.45
     Investigator
    1.33
     investigator
    1.32
    accident
    1.30
     investigation
    1.26
     Investigators
    1.23
     accidents
    1.23
    Activations Density 0.033%

    No Known Activations