© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 117215
    Prev
    Next
    INDEX
    Explanations

    object initialization

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

    This neuron fires on Angular component and modal‐opening boilerplate (e.g. import/@Component blocks and `$modal.open` calls).

    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
    notifyListeners
    -1.05
    </tr>
    -0.82
    
    -0.81
     Архивная
    -0.79
    ――
    -0.78
    \"
    -0.77
    돈
    -0.77
    ógica
    -0.75
    glPopMatrix
    -0.75
    ^
    -0.74
    POSITIVE LOGITS
     {
    3.39
    ({
    2.86
    ,{
    2.67
    ',{
    2.61
    ={
    2.53
     $\{
    2.47
     ({
    2.45
     ={
    2.45
    ",{
    2.39
     {
    2.38
    Activations Density 0.240%

    No Known Activations