© 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. 84016
    Prev
    Next
    INDEX
    Explanations

    Mickey Mouse names

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

    The neuron is highly sensitive to mentions of Disney-related proper names—especially “Disney,” “Mickey,” “Mouse,” and variants like “Micky” or “Mick.”

    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
    潯
    -0.77
     مب
    -0.75
     indulged
    -0.73
    面接
    -0.71
     mirage
    -0.71
    打扰
    -0.70
     intermission
    -0.69
    opens
    -0.68
     vengo
    -0.68
     pleasantly
    -0.67
    POSITIVE LOGITS
     Mouse
    1.80
     mouse
    1.33
     Clubhouse
    1.30
     clubhouse
    1.21
     MOUSE
    1.17
    Mouse
    1.15
    MOUSE
    1.11
    mouse
    1.02
     ears
    1.02
     mice
    0.99
    Activations Density 0.014%

    No Known Activations