© 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. 34-GEMMASCOPE-RES-131K
    4. 116849
    Prev
    Next
    INDEX
    Explanations

    dates and numbers

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

    The neuron strongly activates on tokens containing digits (i.e. numbers or number‐like strings).

    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
    🕒
    -1.04
     disebut
    -0.97
     kartą
    -0.96
     laquelle
    -0.95
     unut
    -0.94
     ہوا
    -0.92
     milyon
    -0.91
     lequel
    -0.91
     kalla
    -0.91
    南宫
    -0.91
    POSITIVE LOGITS
     possiamo
    0.96
     diferite
    0.95
     größe
    0.94
    à
    0.93
     刺繍
    0.91
     lokalen
    0.90
    株式会社
    0.88
     respecting
    0.87
     resolução
    0.86
     recount
    0.85
    Activations Density 0.120%

    No Known Activations