© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 64653
    Prev
    Next
    INDEX
    Explanations

    code and data structures

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

    The neuron fires on occurrences of the identifier “node” (and its variants like “Node”) in code, especially in data‐structure definitions and pointer operations.

    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
    jumu
    -1.02
    tbx
    -1.01
     період
    -0.97
     общий
    -0.96
    第一个
    -0.94
    caccio
    -0.94
    Билгалдахарш
    -0.94
    elli
    -0.94
     mengajak
    -0.94
    协助
    -0.93
    POSITIVE LOGITS
    本科
    0.98
     bronz
    0.98
     Universitaria
    0.98
    国防
    0.96
    ()){
    0.93
    徘
    0.92
     sportif
    0.92
    एं
    0.92
    ☝
    0.92
     visualization
    0.91
    Activations Density 0.015%

    No Known Activations