© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 113944
    Prev
    Next
    INDEX
    Explanations

    embeddings and embedded concepts

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

    the word "embeddings" or "embedding" in technical or scientific contexts.

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

    The neuron activates on occurrences of the word “embed” in any form (e.g. embedding, embeddings, embedded).

    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
     he
    -3.77
    ꔹ
    -3.05
    🧌
    -2.78
    瓩
    -2.78
    enablog
    -2.77
    她
    -2.66
    ⎘
    -2.63
    ꜆
    -2.59
    ?"
    -2.58
     {
    -2.56
    POSITIVE LOGITS
    灕
    3.48
    ⦊
    3.11
    賔
    2.53
    驀
    2.39
    ୈ
    2.38
    欵
    2.30
    ?
    2.19
    *
    2.19
    鄠
    2.19
    考验
    2.16
    Activations Density 0.015%

    No Known Activations