© 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. 37807
    Prev
    Next
    INDEX
    Explanations

    modes of transport

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

    The neuron activates on text describing prison security failures and inmate escapes.

    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
     yzf
    -0.89
     shimano
    -0.82
     gsx
    -0.81
     husqvarna
    -0.80
     jbl
    -0.79
     Partici
    -0.77
    ミッション
    -0.76
    🛺
    -0.75
    键
    -0.75
    bleau
    -0.74
    POSITIVE LOGITS
     vehicles
    3.67
     cars
    3.30
     vehicle
    3.20
     trucks
    3.08
     truck
    2.67
     boats
    2.59
    vehicles
    2.41
     vans
    2.34
     buses
    2.34
     Vehicles
    2.28
    Activations Density 0.241%

    No Known Activations