© 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. 76589
    Prev
    Next
    INDEX
    Explanations

    Posters, boxes, evaluation of derivative

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

    The neuron fires on structural or “boilerplate” tokens in technical or markup‐style text—things like section headings, metadata labels, numeric codes, XML/XSL tags, and other document‐formatting markers.

    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
     Aniston
    -0.71
     Shand
    -0.69
     answers
    -0.67
    ALIAS
    -0.67
     وزارت
    -0.66
    OURCES
    -0.66
    Modulo
    -0.66
    ITOR
    -0.66
     abat
    -0.65
     amat
    -0.65
    POSITIVE LOGITS
     casado
    0.70
    
    0.66
    Bun
    0.65
    cloak
    0.63
    يتر
    0.63
    邳
    0.63
    getreten
    0.62
     Grady
    0.62
     nationals
    0.62
    >())
    0.61
    Activations Density 0.042%

    No Known Activations