© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 101121
    Prev
    Next
    INDEX
    Explanations

    match, case, switch statements

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

    the keyword "match" or "switch" in control flow statements across different programming languages.

    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
    쫀
    -1.91
     '
    -1.77
     and
    -1.73
    gın
    -1.71
    。"
    -1.65
     ('
    -1.64
    dessert
    -1.64
    鬟
    -1.60
    γω
    -1.58
    zestaw
    -1.58
    POSITIVE LOGITS
     the
    2.06
    y
    1.59
    “
    1.52
     they
    1.49
    which
    1.47
    what
    1.46
    ナナ
    1.46
    "";
    1.39
     sif
    1.39
     this
    1.39
    Activations Density 0.006%

    No Known Activations