© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 100265
    Prev
    Next
    INDEX
    Explanations

    C++ inline and constexpr

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

    the keyword "inline" in function declarations across various 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
     you
    -2.23
     we
    -1.67
     damals
    -1.61
     ursprünglich
    -1.53
     The
    -1.50
     zunächst
    -1.46
    矜
    -1.45
     ‘‘
    -1.41
     «
    -1.41
     We
    -1.39
    POSITIVE LOGITS
    4
    2.59
    5
    2.41
    8
    2.33
    6
    2.23
    3
    2.05
    9
    2.02
    7
    1.80
    While
    1.78
    There
    1.70
    ally
    1.63
    Activations Density 0.003%

    No Known Activations