© 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. 1583
    Prev
    Next
    INDEX
    Explanations

    sizes and resolutions

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

    This neuron responds to numeric values (especially standalone digits or dimension-style 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_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
     to
    -2.59
     accedi
    -2.33
     is
    -2.33
     Then
    -2.14
     participó
    -2.00
     visitó
    -1.99
     For
    -1.98
     varies
    -1.96
    .''
    -1.95
     dará
    -1.94
    POSITIVE LOGITS
     dekoratif
    2.27
     organik
    2.19
     arka
    2.09
     kutu
    2.09
     diki
    2.08
     наших
    2.08
     kemer
    2.03
     bebek
    2.02
     baju
    2.02
    usters
    2.02
    Activations Density 0.014%

    No Known Activations