© 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. 7240
    Prev
    Next
    INDEX
    Explanations

    specific noun following "the"

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

    The neuron fires on numeric tokens (multi‐digit 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_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
     heridos
    -1.41
    asca
    -1.38
     cóc
    -1.32
     الأربع
    -1.31
     herido
    -1.29
     втором
    -1.29
     cinq
    -1.27
     quatre
    -1.27
     nová
    -1.21
     trzech
    -1.20
    POSITIVE LOGITS
     particular
    2.27
     given
    1.66
     person
    1.63
     chosen
    1.59
     same
    1.55
     it
    1.55
     specific
    1.49
     betreffenden
    1.47
     associated
    1.40
     item
    1.37
    Activations Density 0.274%

    No Known Activations