© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 90994
    Prev
    Next
    INDEX
    Explanations

    company names and brands

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

    This neuron flags occurrences of corporate or institutional proper names (e.g. brand and 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_34/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
     plátano
    -0.93
    会社
    -0.91
    一二
    -0.84
     Nigerians
    -0.84
     manzana
    -0.83
    ğından
    -0.82
     ябло
    -0.81
    indelijk
    -0.81
     verduras
    -0.79
    Parametros
    -0.78
    POSITIVE LOGITS
     Shahid
    0.96
    NHK
    0.90
    olastic
    0.87
     suuri
    0.85
    agens
    0.85
     ].
    0.83
    Sony
    0.82
    BBC
    0.82
    espn
    0.82
    NBA
    0.81
    Activations Density 0.041%

    No Known Activations