© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 78226
    Prev
    Next
    INDEX
    Explanations

    fields and domains

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

    The neuron detects words that appear as items or conjunctions in enumerated lists or category series (e.g. the “and/y/de” connecting terms and the listed category names).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    ご馳走
    -0.96
     tuvimos
    -0.93
    シカ
    -0.88
    超級
    -0.85
     आवश्यकता
    -0.85
    希望能
    -0.84
    旁邊
    -0.84
    的可
    -0.83
     نقاشی
    -0.82
     نمایید
    -0.81
    POSITIVE LOGITS
     familial
    1.25
     ministerial
    1.20
     enzymatic
    1.16
    toplasmic
    1.10
     Ministerial
    1.09
     clerical
    1.07
     scholastic
    1.04
     fluvial
    1.04
     cinematic
    1.01
     Oceanic
    1.01
    Activations Density 0.167%

    No Known Activations