© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 61472
    Prev
    Next
    INDEX
    Explanations

    orthogonal

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

    This neuron responds to occurrences of the word “orthogonal.”

    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
    乆
    -3.09
    jenigen
    -2.44
     letzten
    -2.42
    "",
    -2.30
     “
    -2.25
    ものに
    -2.25
     
    -2.23
     Their
    -2.20
    >
    -2.19
    瑒
    -2.16
    POSITIVE LOGITS
    悒
    2.88
    全新的
    2.63
    婞
    2.58
    ⼗
    2.55
    ︕
    2.55
    瘣
    2.52
    Z
    2.47
     یا
    2.47
    艫
    2.47
    s
    2.44
    Activations Density 0.005%

    No Known Activations