© 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. 23748
    Prev
    Next
    INDEX
    Explanations

    take exams

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

    The neuron responds to capitalized location names (e.g. “New York State”).

    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
     Approve
    -0.79
     Mantis
    -0.76
    říve
    -0.74
    ソニー
    -0.71
     レイ
    -0.71
     洗面
    -0.69
     เปิด
    -0.68
     Inspect
    -0.68
    kane
    -0.68
     만들
    -0.67
    POSITIVE LOGITS
     taking
    2.22
    Taking
    1.82
     take
    1.69
     Taking
    1.66
    taking
    1.66
     took
    1.55
    受験
    1.37
     takes
    1.34
     exams
    1.30
     takers
    1.30
    Activations Density 0.032%

    No Known Activations