© 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. 75262
    Prev
    Next
    INDEX
    Explanations

    numbers and codes

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

    The neuron detects numeric tokens (digit sequences), i.e. any standalone 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_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
    without
    -0.93
    recently
    -0.93
     ré
    -0.90
    ぜ
    -0.90
     Fahr
    -0.90
    OrEqualTo
    -0.89
     хорошего
    -0.88
    理会
    -0.88
    psd
    -0.88
     corretamente
    -0.88
    POSITIVE LOGITS
     (!__
    1.15
    4
    1.05
     również
    0.96
     letti
    0.96
     balas
    0.96
    Mant
    0.96
     tomat
    0.96
    mathrm
    0.96
     bianchi
    0.96
    apad
    0.94
    Activations Density 0.078%

    No Known Activations