© 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. 92746
    Prev
    Next
    INDEX
    Explanations

    code execution outputs

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

    The main thing this neuron does is detect numeric literal tokens (pure sequences of digits) in code or text.

    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
    involved
    -0.95
    gambarkan
    -0.80
     digelar
    -0.80
    delig
    -0.77
    Ahol
    -0.77
     involved
    -0.77
    ause
    -0.77
    そろそろ
    -0.76
    ebook
    -0.75
    delige
    -0.75
    POSITIVE LOGITS
     apsau
    0.84
     vandens
    0.81
     admirable
    0.78
    警告
    0.77
     warned
    0.77
     Out
    0.76
     INFO
    0.76
     ocurrir
    0.76
    

    0.75
     uefa
    0.75
    Activations Density 0.067%

    No Known Activations