© 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. 22-GEMMASCOPE-RES-131K
    7. 14495
    Prev
    Next
    INDEX
    Explanations

    cities and countries

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

    The neuron strongly activates on proper names and named entities (e.g. place names, product names, organization 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_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
    êtement
    -0.99
    írit
    -0.93
    卫生间
    -0.91
    説明書
    -0.90
     capacitors
    -0.88
     Testament
    -0.88
    aterin
    -0.88
     中古
    -0.87
    gatan
    -0.87
    !"
    -0.87
    POSITIVE LOGITS
    本体
    0.97
    
    0.94
     głów
    0.94
     durante
    0.94
     ethereum
    0.89
    -..
    0.88
     «<
    0.88
     своими
    0.88
     selber
    0.87
     itself
    0.86
    Activations Density 0.199%

    No Known Activations