© 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. 102717
    Prev
    Next
    INDEX
    Explanations

    code structures and imports

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

    opening parentheses and brackets in code, particularly in function definitions and data structures.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron activates on numeric literals (particularly floating-point and integer constants) in code.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     augusti
    -1.45
     yake
    -1.41
     celta
    -1.41
     خودش
    -1.39
     cubana
    -1.38
     godk
    -1.31
     alip
    -1.31
    瑧
    -1.30
     iko
    -1.30
     sentra
    -1.29
    POSITIVE LOGITS
     RoutedEventArgs
    1.63
     EconPapers
    1.49
    担任
    1.44
    uver
    1.42
     It
    1.41
     eerst
    1.40
    %");
    1.40
    --)
    1.39
     cuyas
    1.38
     nosso
    1.37
    Activations Density 0.159%

    No Known Activations