© 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. 10-GEMMASCOPE-RES-131K
    7. 19294
    Prev
    Next
    INDEX
    Explanations

    authentication token

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

    The neuron fires on references to JSON Web Tokens (JWT) and related authentication/token handling.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     também
    -1.45
    Quinta
    -1.34
     interesses
    -1.33
    generally
    -1.32
     ᾿
    -1.30
     staffel
    -1.30
    卺
    -1.28
     può
    -1.27
     ananas
    -1.26
     tranſ
    -1.26
    POSITIVE LOGITS
     as
    1.73
     on
    1.58
     out
    1.47
     focusing
    1.35
     or
    1.33
     during
    1.33
     mid
    1.24
     M
    1.24
     system
    1.23
     S
    1.22
    Activations Density 0.067%

    No Known Activations