© 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. 22-GEMMASCOPE-RES-131K
    7. 16156
    Prev
    Next
    INDEX
    Explanations

    checking login, role, ownership, arguments, permissions, username, connection, status, objects

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

    The neuron fires on programmer-defined identifiers (function, method, or variable names) in code snippets.

    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
     légèrement
    -0.93
    ummy
    -0.85
    וו
    -0.85
     مجموعة
    -0.85
    ज्ञ
    -0.83
     Благодаря
    -0.83
    BUT
    -0.81
     modelleri
    -0.81
    kram
    -0.81
     Een
    -0.80
    POSITIVE LOGITS
     whether
    1.76
    是否
    1.56
     against
    1.45
     before
    1.40
     apakah
    1.21
     with
    1.18
     although
    1.16
     if
    1.16
     existence
    1.15
     by
    1.13
    Activations Density 0.044%

    No Known Activations