© 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. 34-GEMMASCOPE-RES-131K
    7. 38404
    Prev
    Next
    INDEX
    Explanations

    site paths and code

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

    The neuron fires on references to C/C++ header files—that is, tokens ending in “.h” or include-style header filenames.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     després
    -0.78
     HMRC
    -0.75
     εί
    -0.73
     AIC
    -0.73
     Mí
    -0.71
     també
    -0.69
    ("/{
    -0.69
     HAS
    -0.69
     Mayfield
    -0.69
    IsEnabled
    -0.69
    POSITIVE LOGITS
    chere
    0.77
     Mocha
    0.75
    IB
    0.74
    agent
    0.72
    Yan
    0.72
    ContentType
    0.72
    Velocity
    0.71
    HL
    0.71
     false
    0.71
     pearly
    0.70
    Activations Density 0.008%

    No Known Activations