© 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. 24-GEMMASCOPE-2-RES-16K
    7. 13941
    Prev
    Next
    INDEX
    Explanations

    `

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

    This neuron activates on code‐like tokens—especially function or macro calls and other programming/instruction syntax (e.g. names followed by parentheses, uppercase identifiers, memory‐address patterns).

    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_24_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
    ,
    0.65
    .
    0.57
     eigene
    0.56
     wsi
    0.52
    !
    0.51
    -
    0.51
     ilg
    0.50
    各国
    0.50
    各类
    0.50
     catatan
    0.50
    POSITIVE LOGITS
     WOULD
    0.67
     bhij
    0.64
    
    0.64
     avrebbe
    0.61
    youtu
    0.60
    䣨
    0.60
    iería
    0.60
    lső
    0.60
     ബ്രി
    0.59
     serían
    0.59
    Activations Density 0.066%

    No Known Activations