© 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. 22-GEMMASCOPE-RES-131K
    7. 104289
    Prev
    Next
    INDEX
    Explanations

    0x sequences

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

    The neuron is picking out literal constants—especially numeric literals (and the occasional boolean like “true”/“false”) in code.

    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
     impresion
    -1.50
    лтемелер
    -1.49
     kapas
    -1.48
     aasta
    -1.41
     senin
    -1.41
     balon
    -1.39
     hırka
    -1.38
    Màu
    -1.38
     kaos
    -1.36
     olje
    -1.35
    POSITIVE LOGITS
     to
    1.52
     myriad
    1.40
     hugely
    1.27
     pivotal
    1.25
     
    1.23
     tumultuous
    1.23
     trotzdem
    1.21
     overarching
    1.20
     famed
    1.20
     latter
    1.18
    Activations Density 0.001%

    No Known Activations