© 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. 19398
    Prev
    Next
    INDEX
    Explanations

    introduces lists or examples

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

    This neuron detects procedural or methodological cues—words and punctuation that introduce or structure experimental methods and step‐by‐step procedure descriptions.

    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
    鲧
    -1.53
     
    -1.48
    >'+
    -1.41
     BECAUSE
    -1.34
    颡
    -1.33
    футболка
    -1.28
    >");
    -1.28
    –>
    -1.27
     recenti
    -1.27
    antry
    -1.26
    POSITIVE LOGITS
    .
    1.48
     is
    1.36
     роботи
    1.29
    _
    1.24
    まで
    1.23
    ;
    1.22
    :
    1.22
    太多
    1.22
         
    1.17
    了一些
    1.17
    Activations Density 0.578%

    No Known Activations