© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 6111
    Prev
    Next
    INDEX
    Explanations

    python code execution

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

    The neuron activates on occurrences of “.js,” i.e. JavaScript file names or references to JavaScript file extensions.

    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
    ////////////////
    0.64
     પા
    0.61
    δέ
    0.59
     //
    0.59
     Nun
    0.57
    //////////
    0.57
    اہم
    0.55
     &'
    0.55
    ↵
    0.55
    )}_
    0.55
    POSITIVE LOGITS
    គុ
    0.59
     peptide
    0.55
     porcel
    0.54
     divertido
    0.53
     tesla
    0.53
     biomark
    0.52
     mutter
    0.52
     моно
    0.51
     termo
    0.50
     peptides
    0.50
    Activations Density 0.000%

    No Known Activations