© 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. 111032
    Prev
    Next
    INDEX
    Explanations

    Cart or related words

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

    The neuron is highly sensitive to occurrences of the substring “Cartan” (i.e. the proper name “Cartan”).

    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
     Mondial
    -0.73
    capability
    -0.72
     женские
    -0.72
     halv
    -0.69
     Gautam
    -0.69
    Leslie
    -0.69
     отца
    -0.69
    inement
    -0.68
     眼睛
    -0.67
     सु
    -0.67
    POSITIVE LOGITS
     cart
    0.90
     encuentre
    0.89
     Cart
    0.87
     potenza
    0.84
     pelajar
    0.82
    rauch
    0.81
    lrrrr
    0.80
    ongeza
    0.79
     percorso
    0.79
    efe
    0.79
    Activations Density 0.017%

    No Known Activations