© 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. 92431
    Prev
    Next
    INDEX
    Explanations

    # . hpp app Forbes Place

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

    The neuron fires on the structured boilerplate copyright/license header section (e.g. “Copyright …”, “Permission is hereby granted…”).

    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
     Defic
    -0.90
     йыл
    -0.84
     Econom
    -0.80
     Econ
    -0.79
    Tre
    -0.77
     придется
    -0.73
     deficits
    -0.73
    іе
    -0.72
     vector
    -0.69
    ⊇
    -0.69
    POSITIVE LOGITS
    aguchi
    0.79
    dikan
    0.79
    possession
    0.78
    randa
    0.78
    tyczne
    0.77
     Sempre
    0.77
     markiert
    0.76
    ὴν
    0.76
     aeruginosa
    0.76
     sempre
    0.75
    Activations Density 0.027%

    No Known Activations