© 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. 9487
    Prev
    Next
    INDEX
    Explanations

    Nassau locations and variations

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

    The neuron strongly activates on occurrences of the character sequence “Nass,” especially in proper names like “Nassau.”

    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
     unſ
    -2.53
    身后的
    -2.50
    торая
    -2.47
    乆
    -2.41
    쨩
    -2.39
     Tonnen
    -2.36
    一旁的
    -2.34
    一旁
    -2.34
    mudah
    -2.33
     -"
    -2.31
    POSITIVE LOGITS
    ↵
    4.56
    ↵↵
    4.09
    </td>
    2.64
    ’
    2.50
    and
    2.44
    m
    2.44
    鏨
    2.36
    s
    2.28
    o
    2.27
       
    2.20
    Activations Density 0.002%

    No Known Activations