© 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. 111737
    Prev
    Next
    INDEX
    Explanations

    code punctuation

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

    closing parentheses in function calls or conditional statements 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
     has
    -1.66
    ’
    -1.58
     to
    -1.52
    </h3>
    -1.49
    。
    -1.48
     A
    -1.48
     can
    -1.47
     “
    -1.46
     On
    -1.45
     La
    -1.45
    POSITIVE LOGITS
     konsult
    1.96
     filmen
    1.88
     男士
    1.77
     破解
    1.73
     понрави
    1.70
     geograf
    1.68
     ekolog
    1.66
     歐
    1.65
     mikrofon
    1.63
     romantis
    1.63
    Activations Density 0.035%

    No Known Activations