© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 113635
    Prev
    Next
    INDEX
    Explanations

    Major titles and versioning

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

    the word "Major" when it appears in version numbering or as a military/professional title.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron activates on occurrences of the word “major.”

    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
    鶿
    -2.97
    峤
    -2.55
     使っ
    -2.50
     amantes
    -2.50
    篭
    -2.39
     trabajadores
    -2.39
     cereales
    -2.36
    莇
    -2.34
    癟
    -2.34
     adolescentes
    -2.34
    POSITIVE LOGITS
    3
    4.31
    5
    4.25
    7
    3.97
    1
    3.94
    8
    3.91
    6
    3.86
    9
    3.69
    0
    3.66
    4
    3.58
    2
    3.33
    Activations Density 0.018%

    No Known Activations