© 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. 104
    Prev
    Next
    INDEX
    Explanations

    names and numbers

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

    The neuron chiefly fires on capitalized words, in particular proper names and other named entities.

    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
     and
    -1.07
     Kø
    -0.96
    лён
    -0.90
    either
    -0.90
    XN
    -0.89
     either
    -0.85
    小区
    -0.83
     coalitions
    -0.81
     называют
    -0.81
     variedade
    -0.80
    POSITIVE LOGITS
     polícia
    0.91
     anvä
    0.86
    娱
    0.85
    ਔ
    0.82
     informal
    0.82
    kanı
    0.81
    anzia
    0.81
    Families
    0.81
     klassischen
    0.81
     wykor
    0.79
    Activations Density 0.149%

    No Known Activations