© 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. 23860
    Prev
    Next
    INDEX
    Explanations

    scientific publications and citations

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

    DOI (Digital Object Identifier) sequences in academic citations.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron selectively activates on long numeric sequences (e.g. DOIs, citation identifiers) in the text.

    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
    moiselle
    -0.99
     in
    -0.90
     even
    -0.90
    Życiorys
    -0.88
     or
    -0.87
     at
    -0.87
     bella
    -0.85
    boks
    -0.84
    اعات
    -0.84
     pistola
    -0.84
    POSITIVE LOGITS
     apprécié
    0.95
     veranda
    0.89
    ){//
    0.89
     потребуется
    0.88
     perciò
    0.87
    Reklama
    0.84
    十分的
    0.83
    Mitarbeiter
    0.83
     понадобится
    0.83
     góry
    0.83
    Activations Density 0.001%

    No Known Activations