© 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. 22-GEMMASCOPE-RES-131K
    7. 36259
    Prev
    Next
    INDEX
    Explanations

    state of

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

    The neuron strongly activates on named entities—especially party or organization names (e.g. STATE, PEOPLE) and other proper‐noun tokens.

    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
    睁开
    -0.89
    Autowired
    -0.89
    RTEE
    -0.86
     ():
    -0.85
    ！（
    -0.84
    家は
    -0.82
     Ais
    -0.82
    хам
    -0.82
    nąć
    -0.82
    issement
    -0.82
    POSITIVE LOGITS
    reu
    0.93
    üste
    0.85
     besser
    0.84
    不能
    0.83
    hubaneswar
    0.82
    monių
    0.81
    鍙
    0.80
     inaprop
    0.79
     disminu
    0.79
     مست
    0.78
    Activations Density 0.001%

    No Known Activations