© 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. 348
    Prev
    Next
    INDEX
    Explanations

    creative

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

    The neuron is primarily activated by the token “Creative” (and its forms), i.e. it detects occurrences of the word “creative.”

    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
    itek
    -0.77
    auta
    -0.75
    Biografie
    -0.75
     nacionales
    -0.74
    те
    -0.72
    unak
    -0.72
    zou
    -0.72
    enschappe
    -0.70
    boxShadow
    -0.69
    éral
    -0.69
    POSITIVE LOGITS
     creative
    5.41
     creativity
    4.63
    creative
    4.47
     твор
    3.83
    Creative
    3.81
     Creative
    3.75
     artistic
    3.67
     Creativity
    3.47
    Creativity
    3.39
     creatives
    3.22
    Activations Density 0.085%

    No Known Activations