© 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. 22-GEMMASCOPE-RES-131K
    7. 33813
    Prev
    Next
    INDEX
    Explanations

    names followed by compound words

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

    The neuron activates on capitalized tokens that are parts of proper names or named entities.

    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
     camisetas
    -1.53
    Daftar
    -1.29
     televiz
    -1.28
     bicicletas
    -1.28
     innamor
    -1.27
    ᜀ
    -1.27
     descubrió
    -1.27
     nosso
    -1.26
    acaktır
    -1.26
     bailar
    -1.25
    POSITIVE LOGITS
    ฯ
    1.62
    ara
    1.42
    za
    1.42
    at
    1.29
    ha
    1.28
    ate
    1.28
     is
    1.26
    ge
    1.22
    aran
    1.22
    ga
    1.20
    Activations Density 0.056%

    No Known Activations