© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 39039
    Prev
    Next
    INDEX
    Explanations

    technical concepts and code declarations

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

    The neuron specifically detects occurrences of the word “blue.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     لإ
    -1.15
    CRETE
    -1.13
    //!
    -1.11
    :^{
    -1.11
    EMPO
    -1.09
     Gennaio
    -1.09
    vají
    -1.08
    CHOS
    -1.07
    atzes
    -1.05
    ATIVA
    -1.05
    POSITIVE LOGITS
     with
    1.31
     シャンプー
    1.21
    Leírás
    1.20
    Karakter
    1.19
    除非
    1.17
    Ahoj
    1.15
     znaleźć
    1.12
    parece
    1.12
    ächtigen
    1.11
    Lycka
    1.09
    Activations Density 0.000%

    No Known Activations