© 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. 10-GEMMASCOPE-RES-131K
    7. 104931
    Prev
    Next
    INDEX
    Explanations

    fairy tales and fictional characters

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

    This neuron activates on proper names and titles of well-known fairy-tale or mythic characters and stories.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    </strong>
    -1.90
    </h3>
    -1.84
    p
    -1.48
    {
    -1.47
     nordrhein
    -1.46
    {
    -1.44
    風味
    -1.43
    ";
    -1.43
    f
    -1.43
     `<
    -1.42
    POSITIVE LOGITS
    蠖
    1.73
    岽
    1.71
    罴
    1.69
    憷
    1.68
    鸱
    1.63
    鹩
    1.62
    罍
    1.55
    klas
    1.53
    驺
    1.52
     händ
    1.51
    Activations Density 0.003%

    No Known Activations