© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 67510
    Prev
    Next
    INDEX
    Explanations

    number and punctuation sequences

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

    The neuron is primarily activated by numeric tokens (digits and numbers) 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_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
    ”
    -1.66
     dagens
    -1.60
     of
    -1.52
    鎬
    -1.49
     problemet
    -1.45
     sacerd
    -1.39
     boken
    -1.39
     në
    -1.38
     ”
    -1.38
     yaka
    -1.35
    POSITIVE LOGITS
    蒐
    1.55
    驀
    1.43
     gewünschten
    1.38
    emballage
    1.34
    </h3>
    1.31
    hichever
    1.31
    1
    1.27
     girar
    1.27
    hôtel
    1.26
    我先
    1.25
    Activations Density 0.008%

    No Known Activations