© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 9668
    Prev
    Next
    INDEX
    Explanations

    variable declaration and assignment

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

    The neuron fires on code‐identifier tokens—e.g. variable names, class/type names, and similar programmer-defined symbols.

    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
     väč
    -1.07
     ansiedad
    -0.92
     znajd
    -0.86
    greja
    -0.83
     obrázok
    -0.83
    fikasi
    -0.82
    cnbc
    -0.82
    chân
    -0.82
    Kesimpulan
    -0.82
     volna
    -0.81
    POSITIVE LOGITS
    AAD
    0.84
    '>{
    0.84
    ))$.
    0.83
     Cott
    0.82
    ']=='
    0.82
    "].
    0.82
    RIDE
    0.82
    IDES
    0.81
    敛
    0.81
    ɸ
    0.81
    Activations Density 0.006%

    No Known Activations