© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 101128
    Prev
    Next
    INDEX
    Explanations

    lists, headings, and tables

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

    This neuron detects section headings or titles, i.e. words or phrases that mark the start of a new block (like “History,” “Spoiler,” “Product Information,” etc.).

    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
     слегка
    -1.63
     Until
    -1.62
     June
    -1.53
     Took
    -1.52
     limité
    -1.50
     Tuesday
    -1.49
    嵎
    -1.49
     &
    -1.49
     succinct
    -1.48
     amables
    -1.48
    POSITIVE LOGITS
     EMPLOYEE
    1.72
     which
    1.69
    鹧
    1.66
    ⡯
    1.66
     oliver
    1.63
     LADY
    1.61
     superiori
    1.60
     ARROW
    1.59
     again
    1.56
     FEMALE
    1.55
    Activations Density 0.000%

    No Known Activations