© 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. 34-GEMMASCOPE-RES-131K
    7. 102444
    Prev
    Next
    INDEX
    Explanations

    names ending in vowels

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

    This neuron fires on author‐ and date‐metadata in code comments (e.g. “Created by…,” “Date:,” and the associated name and year tokens).

    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
     compagni
    -1.14
     esperti
    -1.06
     dikembangkan
    -0.97
    ensão
    -0.94
    scaleY
    -0.93
     vantaggi
    -0.93
     ditawarkan
    -0.91
     dikeluarkan
    -0.90
     soggetti
    -0.86
     dibangun
    -0.85
    POSITIVE LOGITS
     biscuits
    1.14
     cilia
    1.04
    ci
    1.04
    BigInteger
    1.02
     skis
    0.99
    kli
    0.98
    swiper
    0.98
     biscuit
    0.95
    éli
    0.94
    setIs
    0.94
    Activations Density 0.111%

    No Known Activations