© 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. 251
    Prev
    Next
    INDEX
    Explanations

    prime followed by specific terms

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

    The neuron triggers primarily on occurrences of the word “Prime.”

    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
     lowa
    -0.83
     complying
    -0.81
    ↵↵
    -0.77
     mites
    -0.76
    érèse
    -0.76
     amplify
    -0.75
     broaden
    -0.75
     IFR
    -0.75
     mics
    -0.74
     verfügen
    -0.73
    POSITIVE LOGITS
     mover
    1.59
    Prime
    1.52
     factorization
    1.49
     minister
    1.46
     Prime
    1.42
    val
    1.40
    prime
    1.39
     Minister
    1.38
     prime
    1.23
    Minister
    1.23
    Activations Density 0.013%

    No Known Activations