© 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. 10-GEMMASCOPE-RES-131K
    7. 22210
    Prev
    Next
    INDEX
    Explanations

    proper nouns, materials, or companies

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

    The neuron fires on named entities—especially company or brand names and specialized product/technical terms.

    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
    琑
    -2.77
    うまい
    -2.55
     выбира
    -2.47
    er
    -2.45
    ti
    -2.33
     {
    -2.28
    鏐
    -2.25
     waren
    -2.23
    ates
    -2.22
    
    -2.22
    POSITIVE LOGITS
    *
    3.22
    最后由
    2.58
    比如说
    2.53
     хорошая
    2.48
     października
    2.48
    了一个
    2.48
    但他
    2.44
    ዞ
    2.39
    }}$
    2.36
    沨
    2.36
    Activations Density 0.010%

    No Known Activations