© 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. 89722
    Prev
    Next
    INDEX
    Explanations

    European countries and organizations

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

    The neuron fires on numeric tokens or digit‐based codes (e.g. page numbers, years, document references).

    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
    ológ
    -0.71
    brat
    -0.68
    Organisation
    -0.68
    quette
    -0.68
     клю
    -0.68
    quali
    -0.66
    parole
    -0.66
     悠
    -0.65
    हरा
    -0.65
    insular
    -0.65
    POSITIVE LOGITS
     jack
    0.72
     ridges
    0.71
    xter
    0.68
    هاي
    0.66
     zamknię
    0.66
     replica
    0.66
     melk
    0.66
    ၼ
    0.64
    antoms
    0.64
    licon
    0.64
    Activations Density 0.061%

    No Known Activations