© 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. 10-GEMMASCOPE-RES-131K
    7. 10854
    Prev
    Next
    INDEX
    Explanations

    names and places

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

    The neuron fires strongly on capitalized proper nouns—especially personal or organizational names.

    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
    鳢
    -3.39
    晅
    -3.33
    潆
    -3.14
    涷
    -2.81
     unſ
    -2.77
    沨
    -2.77
    有何
    -2.53
     Each
    -2.53
    躂
    -2.47
    垻
    -2.47
    POSITIVE LOGITS
     \
    2.97
    ли
    2.67
    The
    2.66
    ية
    2.59
            
    2.56
    緜
    2.47
    撿
    2.36
    ور
    2.31
    豨
    2.25
    慫
    2.23
    Activations Density 0.024%

    No Known Activations