© 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. 10-GEMMASCOPE-RES-131K
    7. 86563
    Prev
    Next
    INDEX
    Explanations

    according to

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

    The neuron fires on the word “According,” marking instances where the text attributes information to a source.

    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
    ContentAsync
    -1.95
    䜣
    -1.86
    yled
    -1.84
    sonian
    -1.78
    をご紹介します
    -1.73
    那我
    -1.73
    皷
    -1.73
     inex
    -1.72
    fillment
    -1.70
    を紹介します
    -1.70
    POSITIVE LOGITS
     theses
    2.22
     these
    2.09
     of
    2.00
     была
    1.97
     juſ
    1.89
    で
    1.87
     and
    1.81
    ﻂ
    1.80
    軼
    1.80
     légales
    1.75
    Activations Density 0.019%

    No Known Activations