© 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. 36547
    Prev
    Next
    INDEX
    Explanations

    advertisements or claims of value

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

    The neuron fires on tokens that head titles, headings, or list items—i.e. the very first word or number at the start of a new section.

    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
     three
    -2.97
     four
    -2.84
     two
    -2.78
     eight
    -2.75
     five
    -2.75
     both
    -2.55
     only
    -2.48
     nine
    -2.48
     their
    -2.45
     seven
    -2.42
    POSITIVE LOGITS
     delightfully
    1.95
     unbelievably
    1.87
     goofy
    1.86
     ludicrous
    1.83
     insanely
    1.83
     wacky
    1.82
     gigantic
    1.81
     magnific
    1.80
     DIFFERENT
    1.79
     Dinas
    1.74
    Activations Density 0.000%

    No Known Activations