© 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. 25941
    Prev
    Next
    INDEX
    Explanations

    Q:

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

    The neuron strongly fires on numeric tokens—especially years and other multi‐digit numbers—highlighting sequences of digits 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
    luke
    -0.82
    רְ
    -0.81
    ᴳ
    -0.78
    ֵּ
    -0.74
    ိ
    -0.73
     enfin
    -0.72
    Fonti
    -0.71
     Tapi
    -0.71
    TEST
    -0.71
    phism
    -0.70
    POSITIVE LOGITS
     gie
    0.75
     Беларусь
    0.73
     versi
    0.72
     Salamanca
    0.72
     niz
    0.71
    ddb
    0.70
    underlying
    0.69
     PRET
    0.69
     kab
    0.68
     TAL
    0.68
    Activations Density 0.023%

    No Known Activations