© 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. 65192
    Prev
    Next
    INDEX
    Explanations

    introducing a preferred choice

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

    The neuron fires on the adverb “preferably.”

    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
     katkı
    -2.81
    肫
    -2.64
    ꜆
    -2.45
     parfüm
    -2.34
    闿
    -2.27
    蠖
    -2.14
     orice
    -2.13
     cilt
    -2.11
    せば
    -2.09
    istocene
    -2.08
    POSITIVE LOGITS
    ↵
    3.13
    "
    2.30
    .”
    2.30
     she
    2.25
    while
    2.25
    2
    2.17
     szklan
    2.17
    ’
    2.06
     Hinblick
    2.06
    which
    2.05
    Activations Density 0.003%

    No Known Activations