© 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. 34281
    Prev
    Next
    INDEX
    Explanations

    place names and institutions

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

    The neuron fires on single, capitalized tokens that are parts of named entities such as places, organizations, or institutions.

    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
    獃
    -1.69
    quelles
    -1.61
     lesquelles
    -1.56
    隳
    -1.52
    猻
    -1.51
    蠵
    -1.50
     всички
    -1.47
     小学校
    -1.46
     poissons
    -1.45
    
    -1.45
    POSITIVE LOGITS
     at
    1.58
     As
    1.57
     on
    1.51
     if
    1.48
     To
    1.47
     for
    1.47
    L
    1.47
     At
    1.45
     In
    1.43
    E
    1.42
    Activations Density 0.056%

    No Known Activations