© 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. 93099
    Prev
    Next
    INDEX
    Explanations

    separators and symbols

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

    The neuron strongly responds to code tokens representing numeric‐related operators—especially the “+=” assignment operator (and related increment/decrement symbols like “++” and “--”).

    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
    Hunt
    -0.92
     Mayer
    -0.85
     Hunt
    -0.85
    Temp
    -0.83
     focused
    -0.81
    GeoNames
    -0.81
    ####
    -0.81
    такт
    -0.78
     Pologne
    -0.77
    룡
    -0.75
    POSITIVE LOGITS
     spea
    0.90
     cantit
    0.87
     individuell
    0.84
     SEPAR
    0.83
    ǘ
    0.82
     Gothenburg
    0.82
    arif
    0.82
     acesta
    0.81
     quartile
    0.81
     Umständen
    0.79
    Activations Density 0.036%

    No Known Activations