© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 15952
    Prev
    Next
    INDEX
    Explanations

    code snippets and programming terms

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

    The neuron primarily lights up on programming‐style tokens—especially Android API class and method names (e.g. ContentResolver, CursorLoader) and numeric constants or version numbers in code snippets.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     azon
    0.82
    taxon
    0.73
     Fortnite
    0.68
    spotify
    0.66
     reliably
    0.63
    誂
    0.63
    とその
    0.63
    Spotify
    0.62
    jakarta
    0.61
    Karnataka
    0.61
    POSITIVE LOGITS
    
    0.80
    
    0.78
     zhong
    0.78
    
    0.75
     yuan
    0.70
     Qing
    0.68
    北京
    0.66
     通
    0.66
     Beijing
    0.64
    isShow
    0.64
    Activations Density 0.004%

    No Known Activations