© 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. 44079
    Prev
    Next
    INDEX
    Explanations

    place names

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

    The neuron fires on capitalized proper nouns—especially place names or other 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_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
     accordance
    -2.50
    .’
    -2.48
    ꔹ
    -2.44
    骓
    -2.41
    溦
    -2.39
    觔
    -2.38
     peculiarity
    -2.34
    蘗
    -2.33
    r
    -2.31
    即使
    -2.23
    POSITIVE LOGITS
    1
    2.73
    
    2.73
    
    2.52
    附近的
    2.38
     '
    2.38
    拶
    2.36
    葑
    2.34
     zien
    2.20
    *
    2.16
    浿
    2.09
    Activations Density 0.010%

    No Known Activations