© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 63070
    Prev
    Next
    INDEX
    Explanations

    BMW cars and Bavaria

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

    The neuron strongly activates on alphanumeric strings naming specific BMW models (e.g. “BMW X4,” “BMW X5 xDrive35i,” “BMW M6,” etc.).

    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
    nezeu
    -0.93
     Segen
    -0.83
     ciasc
    -0.83
     ча
    -0.78
    urias
    -0.75
    ̪
    -0.75
    banco
    -0.73
     mitsubishi
    -0.73
     camry
    -0.73
     immagin
    -0.73
    POSITIVE LOGITS
     BMW
    1.53
     Munich
    1.20
    BMW
    1.10
     Bavarian
    1.10
     M
    1.09
     Bim
    1.02
     Bav
    1.02
     Bavaria
    1.02
     ///
    1.02
     Alp
    0.93
    Activations Density 0.011%

    No Known Activations