© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 79031
    Prev
    Next
    INDEX
    Explanations

    social login authentication

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

    The neuron strongly activates on interface labels and phrases for user authentication actions—particularly “Log in” and “Sign up” (and related sign-in/signup UI text).

    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
     الدم
    -0.80
     พร
    -0.80
    folie
    -0.78
    
    -0.77
    らかに
    -0.75
    Bois
    -0.73
    WebSocket
    -0.73
    🥔
    -0.72
     Ankara
    -0.72
     Schloss
    -0.71
    POSITIVE LOGITS
     Google
    2.02
     social
    1.84
     google
    1.73
     Facebook
    1.70
    GOOGLE
    1.52
    Google
    1.49
    google
    1.46
    social
    1.45
     Social
    1.43
     sosial
    1.37
    Activations Density 0.031%

    No Known Activations