© 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. 34-GEMMASCOPE-RES-131K
    7. 82579
    Prev
    Next
    INDEX
    Explanations

    either license, Johnny Wilson, Relaxation

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

    The neuron detects the opening of array or list literals (the “\[” token and immediately following string) in code or data structures.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    houding
    -0.84
    ność
    -0.84
    名は
    -0.81
    strijd
    -0.79
    elski
    -0.78
    Wildcard
    -0.77
     oración
    -0.77
    émy
    -0.76
    čia
    -0.76
    страция
    -0.76
    POSITIVE LOGITS
    culaire
    0.85
     irgendwann
    0.85
     dichiarato
    0.79
     zubere
    0.77
    Cys
    0.76
    0.73
    NO
    0.72
    fazer
    0.71
    Æ
    0.71
    mcu
    0.70
    Activations Density 0.001%

    No Known Activations