© 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. 10-GEMMASCOPE-RES-131K
    7. 19145
    Prev
    Next
    INDEX
    Explanations

    portrait orientation

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

    The neuron mainly detects numeric literals (numbers and version constants) embedded in code or technical 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_10/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
     in
    -2.41
     it
    -2.16
     It
    -2.16
     after
    -2.16
     there
    -1.92
     would
    -1.87
     types
    -1.82
     time
    -1.79
    ± 
    -1.76
     could
    -1.75
    POSITIVE LOGITS
     halen
    1.65
    только
    1.61
     favoris
    1.58
     และ
    1.54
     fortfarande
    1.51
    และ
    1.48
    gelegt
    1.47
    または
    1.45
     小物
    1.45
     หรือ
    1.44
    Activations Density 0.015%

    No Known Activations