© 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. 73196
    Prev
    Next
    INDEX
    Explanations

    Houston followed by names or locations

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

    The neuron activates specifically on occurrences of the place name “Houston.”

    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
     -
    -3.13
    section
    -2.98
     This
    -2.92
    h
    -2.83
    which
    -2.83
     --
    -2.75
    '.
    -2.67
    ㉖
    -2.66
    e
    -2.59
     -"
    -2.56
    POSITIVE LOGITS
    
    3.22
    𐄁
    2.77
    髏
    2.73
    骉
    2.70
    
    2.61
    鹚
    2.47
    鷙
    2.42
    ㆍ
    2.36
    见状
    2.34
    {
    2.31
    Activations Density 0.006%

    No Known Activations