© 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. 75688
    Prev
    Next
    INDEX
    Explanations

    regions and directions

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

    The neuron activates on numeric tokens—especially decimal numbers and percentages—highlighting numerical measurements in the 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
     then
    -1.40
     each
    -1.37
     fühlt
    -1.27
     singola
    -1.27
    就能
    -1.27
     lohnt
    -1.27
     ermöglich
    -1.25
     continuare
    -1.24
     your
    -1.23
     asseg
    -1.21
    POSITIVE LOGITS
     recientemente
    1.46
     including
    1.36
    ßten
    1.34
     other
    1.34
     tzw
    1.33
     incluyendo
    1.31
     Including
    1.29
     Большая
    1.28
    including
    1.27
     Dieser
    1.27
    Activations Density 0.123%

    No Known Activations