© 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. 37947
    Prev
    Next
    INDEX
    Explanations

    membersMembersMEMBERSmemberMember

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

    The neuron responds strongly to low‐frequency or content‐bearing tokens (e.g. numbers, proper names, platform/product names, and other “rare” 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_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
     Youtube
    -0.96
     pdf
    -0.88
     YouTube
    -0.86
     Tweets
    -0.85
     tweeted
    -0.84
     Instagram
    -0.83
     instagram
    -0.82
    instagram
    -0.81
    youtube
    -0.79
    Phosp
    -0.79
    POSITIVE LOGITS
     members
    0.96
    Ning
    0.90
    Members
    0.88
     NATIONS
    0.88
     MEMBERS
    0.87
     desafíos
    0.85
     ห้อง
    0.85
    🍋
    0.85
     member
    0.85
    Member
    0.83
    Activations Density 0.109%

    No Known Activations