© 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. 34-GEMMASCOPE-RES-131K
    7. 111088
    Prev
    Next
    INDEX
    Explanations

    legal or technical context

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

    The neuron consistently activates on numeric tokens (strings of digits), i.e. it picks out numbers.

    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
    tamin
    -0.79
    Hui
    -0.76
    קד
    -0.75
     spl
    -0.72
    祓
    -0.71
     fundraiser
    -0.67
     Кер
    -0.67
    -¿
    -0.66
     reverses
    -0.66
    inau
    -0.65
    POSITIVE LOGITS
    esez
    0.68
     imprim
    0.67
    شویی
    0.66
    ount
    0.64
     singlet
    0.64
    面色
    0.64
    TRIBUT
    0.63
     clung
    0.63
    buzo
    0.62
     envoyé
    0.61
    Activations Density 0.054%

    No Known Activations