© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 119578
    Prev
    Next
    INDEX
    Explanations

    be/been followed by completed actions

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

    The neuron fires on numeric expressions (quantities, measurements, or percentages) 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
     raiſ
    -1.84
    Zubereitung
    -1.76
     knap
    -1.74
     Onze
    -1.67
     Appetit
    -1.66
     Gül
    -1.63
     akti
    -1.63
     tranſ
    -1.63
     EIGHT
    -1.60
     schul
    -1.59
    POSITIVE LOGITS
     for
    2.52
     to
    2.50
     that
    2.17
     on
    2.08
     from
    1.83
     with
    1.74
     see
    1.61
     größere
    1.61
     relatively
    1.56
    ↵
    1.55
    Activations Density 0.074%

    No Known Activations