© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 90705
    Prev
    Next
    INDEX
    Explanations

    Peugeot cars

    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
    少女
    -0.88
    kelig
    -0.88
    ✂
    -0.86
    glfw
    -0.84
    уз
    -0.83
    Bomb
    -0.82
    рку
    -0.82
     सुवि
    -0.81
    TintColor
    -0.81
    dAtA
    -0.77
    POSITIVE LOGITS
     Peugeot
    1.30
     Lion
    0.96
    peugeot
    0.90
    Peugeot
    0.88
    Lion
    0.83
     lion
    0.81
    ライオン
    0.79
     Löwen
    0.78
     Henson
    0.75
    Nbr
    0.74
    Activations Density 0.009%

    No Known Activations