© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 105357
    Prev
    Next
    INDEX
    Explanations

    list, array, map assignments

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

    variable declarations or initializations involving collections or data structures (like List, array, vector, or dictionary) in programming code.

    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
    2
    -2.30
    3
    -2.11
    6
    -2.05
    7
    -1.99
    8
    -1.93
    5
    -1.90
    4
    -1.84
    9
    -1.72
    1
    -1.59
     ultimi
    -1.58
    POSITIVE LOGITS
     poderosos
    1.73
     których
    1.65
    sphin
    1.60
     которых
    1.58
     variados
    1.57
     aprendiz
    1.57
     lác
    1.52
    ௜
    1.51
     Кла
    1.51
     to
    1.49
    Activations Density 0.012%

    No Known Activations