© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 39366
    Prev
    Next
    INDEX
    Explanations

    logging and timestamps

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

    The neuron flags logging‐related identifiers and calls (e.g. “logging,” “logger,” “log,” “error,” “console.error,” “getLogger”).

    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
     prêtres
    -0.95
     aguj
    -0.95
    只剩
    -0.93
     sacerdotes
    -0.93
    importation
    -0.92
    そうに
    -0.92
     oído
    -0.91
     koš
    -0.91
     chré
    -0.91
    alarme
    -0.90
    POSITIVE LOGITS
    ַּ
    1.02
    (´
    0.93
    toInt
    0.93
     [],
    
    0.92
     demografica
    0.91
     ideolog
    0.89
    uhan
    0.88
    0.88
    顧客
    0.86
    yPos
    0.86
    Activations Density 0.001%

    No Known Activations