© 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. 103675
    Prev
    Next
    INDEX
    Explanations

    BMW cars and parts

    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
     hypothesized
    -0.82
    pendenti
    -0.79
    kungan
    -0.75
     supervisors
    -0.74
     Oklahoma
    -0.74
    imantan
    -0.73
    Buhari
    -0.73
    禰
    -0.72
    tles
    -0.71
    newtheorem
    -0.70
    POSITIVE LOGITS
     BMW
    2.23
    BMW
    1.94
     bmw
    1.52
    bmw
    1.45
     Munich
    1.32
     Bavarian
    1.21
     Bavaria
    1.13
    宝马
    1.08
    Munich
    1.07
     Bayern
    0.96
    Activations Density 0.007%

    No Known Activations