© 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. 39486
    Prev
    Next
    INDEX
    Explanations

    certificates and awards

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

    The neuron activates on words naming or describing awards, honors, certificates, or trophies and their issuance.

    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
     significantly
    -1.09
    ampire
    -1.07
     trochu
    -1.04
    beiten
    -1.04
    笵
    -1.02
    heiros
    -1.00
    天才
    -1.00
     okolo
    -0.99
    akhstan
    -0.99
     blandt
    -0.97
    POSITIVE LOGITS
     from
    1.55
     ottenuto
    1.30
     certificates
    1.26
    )=>{
    1.24
    公演
    1.20
    ]));
    1.17
     certificate
    1.14
    lierung
    1.13
     ditawarkan
    1.11
    ()]
    1.10
    Activations Density 0.016%

    No Known Activations