© 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. 34-GEMMASCOPE-RES-131K
    7. 49486
    Prev
    Next
    INDEX
    Explanations

    code syntax for lambda expressions

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

    The neuron fires on numeric literals (integer tokens) in the text.

    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
     lavorato
    -0.96
     trattato
    -0.92
     getResources
    -0.92
    ╒
    -0.88
     Conferencia
    -0.88
     Inicial
    -0.88
     tractors
    -0.84
     bambina
    -0.82
     tourner
    -0.82
     getIntent
    -0.82
    POSITIVE LOGITS
     new
    1.86
    null
    1.58
     null
    1.55
    new
    1.54
     typeof
    1.36
    typeof
    1.34
     out
    1.34
    true
    1.29
     such
    1.28
     true
    1.26
    Activations Density 0.013%

    No Known Activations