© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 11290
    Prev
    Next
    INDEX
    Explanations

    unused code or variables

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

    The neuron responds to programming‐style error or warning tokens (e.g. "undefined", "unread") in code or log messages.

    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_31_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
    丶
    0.50
    ">–
    0.50
     disordered
    0.49
     Lumpur
    0.49
     apartness
    0.48
     nuis
    0.47
     Proses
    0.46
    適用
    0.45
    "+"
    0.44
    鈈
    0.44
    POSITIVE LOGITS
     vars
    0.64
    েনার
    0.62
    iffen
    0.61
     potion
    0.60
    éder
    0.59
     குண
    0.59
     BasicContainer
    0.58
    vars
    0.57
    ούν
    0.57
     variables
    0.57
    Activations Density 0.000%

    No Known Activations