© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 98585
    Prev
    Next
    INDEX
    Explanations

    modeldata structure definitions

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

    This neuron responds to code identifier tokens (class names, method/property/variable names) in programming snippets.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    齁
    -1.10
    
    -1.06
     प्रत्येक
    -1.03
     lamentable
    -1.01
    vettes
    -1.00
     strikingly
    -0.99
     astounding
    -0.98
     fotografii
    -0.97
     Име
    -0.94
    僰
    -0.93
    POSITIVE LOGITS
     by
    1.15
     if
    1.12
     provided
    1.05
     of
    0.99
    by
    0.94
    ilyen
    0.94
     brought
    0.90
    ياه
    0.87
    ранее
    0.87
     exercising
    0.86
    Activations Density 0.005%

    No Known Activations