© 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. 10-GEMMASCOPE-RES-131K
    7. 112306
    Prev
    Next
    INDEX
    Explanations

    code delimiters like `]`

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

    array indexing operations with closing brackets.

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

    The neuron strongly activates on numeric literals (especially array indexes or other numbers) 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
     extremadamente
    -1.35
     Unsere
    -1.35
     maravilh
    -1.31
     maravilhoso
    -1.31
     extremamente
    -1.30
     інших
    -1.29
    もありますが
    -1.27
    はもちろん
    -1.27
     infinitely
    -1.27
    rahat
    -1.26
    POSITIVE LOGITS
     gustaba
    1.55
    💎
    1.39
    ⚔
    1.32
    
    1.32
    🚗
    1.31
    一些
    1.26
     насос
    1.25
    因為
    1.24
    😐
    1.24
    😓
    1.23
    Activations Density 0.018%

    No Known Activations