© 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. 22385
    Prev
    Next
    INDEX
    Explanations

    names and their immediate context

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

    The neuron fires most strongly on capitalized personal names (especially surnames) in running text.

    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
     The
    -3.00
     ---
    -2.69
     et
    -2.66
     (&
    -2.64
     количество
    -2.64
    
    -2.59
    
    -2.47
    </b>
    -2.44
     целью
    -2.42
    ↵↵
    -2.36
    POSITIVE LOGITS
    逦
    3.53
    鸶
    3.22
    菪
    2.97
     indiví
    2.83
     тебя
    2.83
    $
    2.81
    ᯾
    2.77
    殽
    2.77
    奩
    2.66
    鹇
    2.64
    Activations Density 0.008%

    No Known Activations