© 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. 10-GEMMASCOPE-RES-131K
    7. 85111
    Prev
    Next
    INDEX
    Explanations

    promise, stipulation, not to

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

    The neuron fires on tokens representing numeric values—digits or numbers, including integers and decimals.

    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
     detain
    -1.45
     Commencez
    -1.34
     tény
    -1.32
     practiced
    -1.28
    haviours
    -1.27
     Souhaitez
    -1.24
     happ
    -1.23
    ználat
    -1.22
    openSession
    -1.21
    我们在
    -1.20
    POSITIVE LOGITS
     that
    2.03
     last
    1.66
    is
    1.58
    only
    1.46
     unless
    1.45
    go
    1.43
    erweise
    1.41
    as
    1.38
    os
    1.37
    no
    1.37
    Activations Density 0.059%

    No Known Activations