© 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. 22-GEMMASCOPE-RES-131K
    7. 73369
    Prev
    Next
    INDEX
    Explanations

    questions and academic writing

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

    The neuron flags imperative prompts that ask the reader to create or write a list.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    ...»
    -1.07
     informa
    -1.07
     شركة
    -1.05
     milliard
    -1.05
     ECONOM
    -1.03
     rapor
    -1.02
     takk
    -1.02
     lana
    -1.02
     网站
    -1.02
    ★☆
    -1.01
    POSITIVE LOGITS
     your
    1.96
     why
    1.52
     essay
    1.30
     
    1.26
    зий
    1.25
     how
    1.20
    或者
    1.17
     düşün
    1.16
     yourself
    1.15
     Vergnügen
    1.13
    Activations Density 0.013%

    No Known Activations