© 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. 22-GEMMASCOPE-RES-131K
    7. 34880
    Prev
    Next
    INDEX
    Explanations

    add, append, or create code elements

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

    The neuron fires on calls that add items to collections (e.g. “.add(” or “append(”).

    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
     to
    -0.98
     getSelected
    -0.92
    揶
    -0.86
    гаре
    -0.86
     including
    -0.84
     ott
    -0.82
    ofile
    -0.82
     also
    -0.82
     redaktion
    -0.81
    DrawerToggle
    -0.81
    POSITIVE LOGITS
    這樣
    1.06
    每個
    0.99
    Каждый
    0.95
     of
    0.94
     poches
    0.94
    に追加
    0.93
    Mvh
    0.93
     hígado
    0.93
    unico
    0.93
     this
    0.92
    Activations Density 0.001%

    No Known Activations