© 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. 10231
    Prev
    Next
    INDEX
    Explanations

    function definitions with parentheses

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

    The neuron flags long non-word sequences such as URLs, file paths, timestamps, or other digit-heavy “noise” tokens.

    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
     {}
    0.99
     [,
    0.89
     \)
    0.88
     \}
    0.83
     {
    0.82
     [*
    0.82
     {*}
    0.82
     (*)
    0.80
     [--
    0.80
     »
    0.80
    POSITIVE LOGITS
    ){
    2.45
    (){
    2.39
    "){
    2.39
    '){
    2.33
    )){
    2.28
    ]){
    2.25
    ()){
    2.20
    ')){
    2.08
    ")){
    2.05
    }){
    1.95
    Activations Density 0.008%

    No Known Activations