© 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. 202
    Prev
    Next
    INDEX
    Explanations

    molecular engineering

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

    publication years and dates in scholarly articles and legal documents.

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

    The neuron activates on standalone numeric tokens (e.g. volume numbers, years, page numbers) typically found in bibliographic or metadata sections.

    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
    atorship
    -0.94
    β
    -0.89
     at
    -0.89
    σιμοποι
    -0.86
     incorrect
    -0.86
     geweest
    -0.85
    lė
    -0.84
     location
    -0.83
     депре
    -0.83
     septiembre
    -0.83
    POSITIVE LOGITS
     escolh
    0.88
     doká
    0.85
    的力量
    0.83
     upvotes
    0.83
    okolade
    0.83
     ネタバレ
    0.83
     majú
    0.83
    ᵑ
    0.83
     vytvá
    0.83
     ponú
    0.83
    Activations Density 0.001%

    No Known Activations