© 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. 34-GEMMASCOPE-RES-131K
    7. 77054
    Prev
    Next
    INDEX
    Explanations

    introductions and titles

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

    The neuron flags metadata tokens—proper names, dates, and other factual identifiers in the text.

    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
     Professors
    -0.79
     WL
    -0.74
    ISES
    -0.70
     Custom
    -0.70
     экспер
    -0.69
     Suggestion
    -0.68
     bombs
    -0.67
    拍攝
    -0.67
    แสดง
    -0.67
     gov
    -0.67
    POSITIVE LOGITS
     supervising
    0.91
     redonda
    0.85
    getic
    0.85
    mechanical
    0.84
     episodes
    0.83
     ljud
    0.82
     mechanical
    0.81
    ęło
    0.81
     serialize
    0.81
     storyboard
    0.81
    Activations Density 0.022%

    No Known Activations