© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 60612
    Prev
    Next
    INDEX
    Explanations

    oauth and authentication

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

    The neuron fires on alphanumeric identifiers that mix letters and digits (e.g. “sqlite3”, “oauth2”, “xlsx”, “chromedriver”).

    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
     According
    -1.45
    ︲
    -1.34
    蠖
    -1.34
    nachron
    -1.28
    madeus
    -1.28
     queste
    -1.24
     trug
    -1.21
     intorno
    -1.20
     attorno
    -1.19
    z
    -1.19
    POSITIVE LOGITS
    わずか
    1.57
    Including
    1.41
    ꯱
    1.41
    
    1.34
    掀
    1.30
     ARISING
    1.29
     incluidas
    1.27
     including
    1.27
    Dữ
    1.25
    thiết
    1.23
    Activations Density 0.102%

    No Known Activations