© 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. 22-GEMMASCOPE-RES-131K
    7. 36568
    Prev
    Next
    INDEX
    Explanations

    numbers in text

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

    This neuron responds to standalone numeric tokens “9.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     and
    -1.68
     or
    -1.52
    0
    -1.30
     zawsze
    -1.26
    มัน
    -1.26
    Toul
    -1.17
    佼
    -1.10
    祷
    -1.08
    1
    -1.05
     sempre
    -1.03
    POSITIVE LOGITS
     ensaio
    1.55
    がありますが
    1.51
     semelh
    1.43
    糁
    1.43
     conster
    1.37
     relógio
    1.30
     painel
    1.29
    cji
    1.25
    桡
    1.25
     Excelente
    1.23
    Activations Density 0.007%

    No Known Activations