© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 77599
    Prev
    Next
    INDEX
    Explanations

    URLs for forums, galleries, or threads

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

    The neuron strongly activates on numeric tokens or digit sequences (e.g. IDs, version numbers, URLs, and other numbers).

    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
    ürze
    -0.79
    idea
    -0.75
    Τα
    -0.74
    Go
    -0.73
    Pro
    -0.70
     grá
    -0.69
     intrinsic
    -0.69
     Naturally
    -0.68
    Naturally
    -0.68
    Maximum
    -0.68
    POSITIVE LOGITS
    thur
    0.84
    threads
    0.81
    thread
    0.78
     thread
    0.75
    Elsa
    0.74
     threads
    0.74
     diy
    0.73
     costing
    0.69
     cityscape
    0.69
     realizarse
    0.69
    Activations Density 0.007%

    No Known Activations