© 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. 22-GEMMASCOPE-RES-131K
    7. 98367
    Prev
    Next
    INDEX
    Explanations

    making one's head spin

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

    The neuron lights up on words and short phrases that serve as emphatic intensifiers or comparative/hyperbolic markers (e.g. “positively,” “more…than,” “really can’t be,” “make your head spin”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     encontrará
    -0.84
    リット
    -0.83
     миллионов
    -0.82
    janos
    -0.82
    ularis
    -0.82
    ಢ
    -0.80
    杩
    -0.79
    ҙ
    -0.78
    umbus
    -0.77
    yaç
    -0.76
    POSITIVE LOGITS
     &&
    0.96
     amazed
    0.96
     almost
    0.95
     aço
    0.94
     hardly
    0.90
     náv
    0.89
     comparable
    0.89
     alumínio
    0.87
     unbelievable
    0.86
     fronteras
    0.84
    Activations Density 0.031%

    No Known Activations