© 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. 10-GEMMASCOPE-RES-131K
    7. 40670
    Prev
    Next
    INDEX
    Explanations

    Related content headings

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

    This neuron detects sidebar or header UI elements showing numeric counts (e.g. “Related Articles 205,” “Related Posts 165,” share/article counters).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     an
    -1.75
     a
    -1.66
     as
    -1.61
     in
    -1.52
    请联系
    -1.51
     Because
    -1.50
     with
    -1.48
    большой
    -1.45
     bereiken
    -1.40
    karena
    -1.38
    POSITIVE LOGITS
    熥
    1.64
     オレンジ
    1.51
    ↵↵
    1.46
     做
    1.42
     quando
    1.41
     白い
    1.38
    atação
    1.38
    sediaan
    1.38
     autres
    1.34
    sibilities
    1.34
    Activations Density 0.017%

    No Known Activations