© 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. 34-GEMMASCOPE-RES-131K
    7. 54076
    Prev
    Next
    INDEX
    Explanations

    Quaternion identity

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

    This neuron activates on code identifiers for math/graphics types and constants—especially class names for transformations (e.g. Matrix4x4, Quaternion) and similarly styled symbols.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    蔼
    -0.79
    Serum
    -0.78
    رفت
    -0.73
     Bene
    -0.73
     ロン
    -0.73
     アウター
    -0.71
     đào
    -0.71
     menghabiskan
    -0.69
     தே
    -0.69
    atives
    -0.69
    POSITIVE LOGITS
     identity
    0.91
    identity
    0.88
    medias
    0.81
     Huck
    0.69
    articulo
    0.68
    {{-
    0.68
    Look
    0.65
     singen
    0.65
    tager
    0.65
    炊
    0.65
    Activations Density 0.027%

    No Known Activations