© 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. 109017
    Prev
    Next
    INDEX
    Explanations

    words starting with car

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

    The neuron is detecting occurrences of the substring “Car,” i.e. tokens beginning with “Car.”

    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
    と
    -0.95
    tagena
    -0.88
     invoked
    -0.83
     Lympho
    -0.79
    職場
    -0.79
    風景
    -0.77
    が
    -0.77
     Höhen
    -0.76
    テク
    -0.75
    โน
    -0.75
    POSITIVE LOGITS
     Car
    1.47
    Car
    1.25
     car
    1.23
    car
    1.05
    oly
    0.92
     kultury
    0.91
     CAR
    0.86
    opcional
    0.84
    hae
    0.83
    unternehmen
    0.82
    Activations Density 0.028%

    No Known Activations