© 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. 103617
    Prev
    Next
    INDEX
    Explanations

    well known

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

    The neuron fires on occurrences of the word “known,” especially in the common phrase “well‐known.”

    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
     It
    -2.52
    ?
    -2.05
     quando
    -2.00
     häufigsten
    -1.98
     необходимо
    -1.97
     cuando
    -1.92
     continúas
    -1.92
    狃
    -1.88
     می‌تواند
    -1.84
     כאשר
    -1.84
    POSITIVE LOGITS
    謇
    1.95
    狁
    1.95
    f
    1.91
    蒹
    1.84
    vám
    1.82
    賒
    1.81
    Ꮉ
    1.80
    ㆆ
    1.80
    疍
    1.77
    known
    1.75
    Activations Density 0.017%

    No Known Activations