© 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. 10-GEMMASCOPE-RES-131K
    7. 113650
    Prev
    Next
    INDEX
    Explanations

    authentication and login systems

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

    references to authentication-related code, libraries, or functionality in programming contexts.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
    0
    -1.97
     the
    -1.55
     But
    -1.45
     brasile
    -1.33
     kadar
    -1.27
    
    -1.23
     уж
    -1.18
    一部分
    -1.18
    -
    -1.16
     freaking
    -1.15
    POSITIVE LOGITS
    只有
    1.55
    )]:
    1.52
    يس
    1.45
     who
    1.41
    Only
    1.38
    ℏ
    1.37
     only
    1.35
     để
    1.34
    )>>
    1.32
    只能
    1.31
    Activations Density 0.004%

    No Known Activations