© 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. 55749
    Prev
    Next
    INDEX
    Explanations

    irregular galaxy

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

    The main thing this neuron does is detect numeric tokens (digits and numbers) often used as data values or measurements.

    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
     ziemi
    -0.74
    ✘
    -0.73
    盒
    -0.71
    onha
    -0.70
     orally
    -0.69
     jost
    -0.68
     Baylor
    -0.68
     pilgrimage
    -0.66
    rån
    -0.66
    setChecked
    -0.65
    POSITIVE LOGITS
     disk
    0.84
     exponential
    0.81
    phological
    0.73
    exponential
    0.72
     morphological
    0.72
     THINGS
    0.69
    wurde
    0.69
    ని
    0.69
    NGC
    0.69
    ugin
    0.68
    Activations Density 0.039%

    No Known Activations