© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 101410
    Prev
    Next
    INDEX
    Explanations

    before or after specific years

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

    The neuron responds to any token containing digits (i.e. numbers, years, decimals).

    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
     alcuni
    -1.50
    </em>
    -1.46
    </strong>
    -1.31
     alcune
    -1.30
     terakhir
    -1.30
    OMA
    -1.27
    ANTES
    -1.25
    haft
    -1.23
    matchCondition
    -1.22
    МЕН
    -1.22
    POSITIVE LOGITS
     than
    1.91
     to
    1.27
     who
    1.18
    Schule
    1.16
    ↵
    1.16
     people
    1.15
    鍬
    1.13
     znamená
    1.12
     pareció
    1.12
     likely
    1.11
    Activations Density 0.031%

    No Known Activations