© 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. 12318
    Prev
    Next
    INDEX
    Explanations

    error handling check

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

    The neuron responds to package import path strings (i.e. tokens containing slash‐separated module or package names).

    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
     WHILE
    0.78
     while
    0.76
    ながら
    0.73
     While
    0.70
    while
    0.67
     mientras
    0.66
     Protein
    0.66
    而
    0.62
    While
    0.61
     uint
    0.61
    POSITIVE LOGITS
     err
    0.87
    err
    0.77
    defer
    0.74
    _,
    0.74
     _,
    0.69
    ERR
    0.61
    Err
    0.59
     postponement
    0.58
    pav
    0.58
    autan
    0.56
    Activations Density 0.002%

    No Known Activations