© 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. 31640
    Prev
    Next
    INDEX
    Explanations

    closing parentheses or braces

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

    The neuron responds strongly to comparison operators (e.g. ==, !=, ===, !==).

    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
    avaş
    -1.05
     surtout
    -1.04
    curities
    -0.97
     notamment
    -0.95
     soprattutto
    -0.94
     जाती
    -0.93
    providedIn
    -0.92
    まりました
    -0.92
    onedDateTime
    -0.89
     など
    -0.88
    POSITIVE LOGITS
     then
    1.47
    Then
    1.30
     {
    1.30
     entonces
    1.27
    tedy
    1.24
     {
    1.14
    ：
    1.12
     Then
    1.10
     allora
    1.02
     wtedy
    1.02
    Activations Density 0.015%

    No Known Activations