© 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. 119418
    Prev
    Next
    INDEX
    Explanations

    opening delimiter syntax

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

    opening curly braces in code, particularly in function definitions and object literals.

    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
    o
    -2.61
     \
    -2.08
    s
    -2.06
    v
    -1.92
    ଃ
    -1.86
     {
    -1.79
    or
    -1.78
     ''
    -1.77
    殽
    -1.75
     â
    -1.73
    POSITIVE LOGITS
     și
    2.02
    𝔻
    1.83
     explicado
    1.77
    
    1.73
     médicos
    1.73
    qtt
    1.73
    utivos
    1.70
     conversar
    1.68
     dizaines
    1.63
     blancas
    1.62
    Activations Density 0.001%

    No Known Activations