© 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. 115556
    Prev
    Next
    INDEX
    Explanations

    charter school

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

    The neuron strongly activates on mentions of “charter schools” and closely related institutional‐education terms.

    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
     Bridal
    -0.84
    lung
    -0.80
    ците
    -0.79
     PRET
    -0.78
    Pulp
    -0.77
    ῇ
    -0.74
     Chemicals
    -0.73
     выя
    -0.73
    Etimología
    -0.73
    硕士
    -0.71
    POSITIVE LOGITS
     charter
    2.88
     Charter
    2.33
    charter
    2.16
    Charter
    2.09
     charters
    1.78
     chartered
    1.43
     char
    1.30
     school
    1.27
     Charters
    1.16
     magnet
    1.12
    Activations Density 0.024%

    No Known Activations