© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 48083
    Prev
    Next
    INDEX
    Explanations

    correlation functions and developmental trajectories

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

    The neuron activates on technical physics jargon—especially terms and phrases related to thermal QCD analyses (e.g. “thermal,” “QCD,” “sum rules,” “temperature,” etc.).

    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
    strup
    -0.77
    laku
    -0.71
     pengh
    -0.69
    веси
    -0.68
     accion
    -0.68
     dov
    -0.68
     diciembre
    -0.67
    )++;
    -0.66
     Sté
    -0.65
    ضاف
    -0.64
    POSITIVE LOGITS
     correl
    1.05
    NDR
    0.84
     корре
    0.81
     Gmail
    0.78
     inserir
    0.77
     corre
    0.75
    setWindow
    0.75
    ห
    0.75
     whitelist
    0.74
    IONE
    0.74
    Activations Density 0.029%

    No Known Activations