© 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. 104674
    Prev
    Next
    INDEX
    Explanations

    switch case statements

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

    the keyword "case" in switch statements across 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
     the
    -2.03
     of
    -1.79
    },
    -1.72
     it
    -1.53
    t
    -1.52
     also
    -1.46
    le
    -1.45
    la
    -1.45
    ↵↵
    -1.43
     أخرى
    -1.41
    POSITIVE LOGITS
     jednom
    1.63
     Entfer
    1.56
     yalnızca
    1.55
    dział
    1.55
    świę
    1.54
    ACJA
    1.51
     disminu
    1.51
     místě
    1.50
    larımız
    1.49
     делает
    1.48
    Activations Density 0.003%

    No Known Activations