© 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. 34-GEMMASCOPE-RES-131K
    7. 91765
    Prev
    Next
    INDEX
    Explanations

    numbers and initialisms

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

    The neuron flags numeric tokens—especially multi‐digit numbers and counts (e.g. bedroom/bathroom counts, prices, years)—in real‐estate listing 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
     Templo
    -0.93
    よろしく
    -0.93
     fevere
    -0.90
    徊
    -0.90
     subtly
    -0.88
    pośred
    -0.87
     Aé
    -0.87
     ujarnya
    -0.87
     vaksinasi
    -0.87
     licor
    -0.87
    POSITIVE LOGITS
     MLS
    0.94
     EIGHT
    0.91
    Descriere
    0.91
    eight
    0.89
    ット
    0.88
    shows
    0.88
     FIRST
    0.87
     первые
    0.86
     STARTED
    0.85
    Accordion
    0.84
    Activations Density 0.003%

    No Known Activations