© 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. 19051
    Prev
    Next
    INDEX
    Explanations

    reporting information from sources

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

    The neuron fires on the word “according” (especially in the phrase “according to”), i.e. source‐attribution cues.

    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
     the
    -2.08
    we
    -2.05
     мы
    -1.99
    both
    -1.77
     
    -1.73
     sowohl
    -1.68
     ด้วย
    -1.65
    ご連絡
    -1.65
     \&
    -1.65
     t
    -1.65
    POSITIVE LOGITS
    蕯
    2.48
    饪
    2.13
     休閒
    2.11
     umano
    2.09
     bogotá
    2.08
     londres
    2.06
     daer
    2.05
     eene
    2.03
    の葉
    2.02
    
    2.00
    Activations Density 0.017%

    No Known Activations