© 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. 34-GEMMASCOPE-RES-131K
    7. 48921
    Prev
    Next
    INDEX
    Explanations

    offroad Jeep expedition

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

    This neuron fires most strongly on words in a technical automotive discussion—especially about winches, airflow over radiators, and Jeep accessory installation.

    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
    ṙ
    -0.98
    әрмәләр
    -0.85
     cereales
    -0.84
    ₤
    -0.83
     bicycle
    -0.83
     krim
    -0.82
     bmx
    -0.82
    Ғ
    -0.81
    ragende
    -0.81
    UMES
    -0.79
    POSITIVE LOGITS
     Moab
    1.42
     offroad
    1.37
     Jeep
    1.20
     articulation
    1.13
     expedition
    1.13
     Expedition
    1.11
     IFS
    1.08
     lockers
    1.07
     Quadrat
    1.06
    Expedition
    1.05
    Activations Density 0.027%

    No Known Activations