© 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. 34-GEMMASCOPE-RES-131K
    7. 79028
    Prev
    Next
    INDEX
    Explanations

    array indexing or objectAtIndex

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

    The neuron fires on programmer-defined identifiers (variable names) 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_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
     pierwsze
    -0.94
     hvor
    -0.88
     أول
    -0.88
     anything
    -0.86
     everything
    -0.85
     its
    -0.85
     første
    -0.85
     first
    -0.83
    ("
    -0.81
     jede
    -0.81
    POSITIVE LOGITS
    第
    1.41
    [
    1.27
     [
    1.20
    '][
    1.19
     objectAtIndex
    1.16
    "][
    1.06
    [$
    1.05
    although
    0.99
     at
    0.91
    '][$
    0.90
    Activations Density 0.009%

    No Known Activations