© 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. 39487
    Prev
    Next
    INDEX
    Explanations

    articles and dates

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

    The neuron specializes in spotting document‐structure and metadata markers—things like section headers, formatting delimiters, uppercase keywords, and other structural tokens.

    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
    なんですね
    -1.18
    なのかな
    -1.16
    なのだ
    -1.12
     many
    -1.08
    Роз
    -1.00
    なもの
    -1.00
     عليكم
    -0.97
     limitada
    -0.95
    Asimismo
    -0.94
    なんだろう
    -0.93
    POSITIVE LOGITS
     🥰
    0.99
     ...........
    0.97
     🤗
    0.95
     ............
    0.94
     漫画
    0.94
     .............
    0.94
     ........
    0.92
     ^_^
    0.91
     .........
    0.90
     小学
    0.89
    Activations Density 0.004%

    No Known Activations