© 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. 10-GEMMASCOPE-RES-131K
    7. 99199
    Prev
    Next
    INDEX
    Explanations

    visual, line, dimension

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

    The neuron consistently lights up on the very first subword piece of longer content words (i.e. the initial token of multi‐piece words).

    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
     maioria
    -1.49
     Prozent
    -1.47
     để
    -1.46
    ྂ
    -1.44
    眛
    -1.41
    どちらも
    -1.38
     техника
    -1.38
     prisão
    -1.38
     assorted
    -1.37
    tricos
    -1.34
    POSITIVE LOGITS
    しに
    1.49
     також
    1.47
     Wartawan
    1.45
     Majesté
    1.44
    ностях
    1.41
    ktioner
    1.38
     beroep
    1.37
     répondit
    1.36
    CardBody
    1.36
     ссылки
    1.34
    Activations Density 0.077%

    No Known Activations