© 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. 69847
    Prev
    Next
    INDEX
    Explanations

    file comments

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

    The neuron primarily activates on numeric tokens (i.e. numbers) throughout the document.

    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
     ose
    -0.73
     Tf
    -0.73
     gifts
    -0.71
     authorship
    -0.70
    multirow
    -0.68
     XK
    -0.67
    Elke
    -0.67
     session
    -0.67
     Saunders
    -0.66
    अप
    -0.66
    POSITIVE LOGITS
    造成的
    0.74
     сер
    0.72
    differential
    0.71
    phospho
    0.67
     differentially
    0.62
     within
    0.62
     quedando
    0.61
    perry
    0.61
     data
    0.60
    なさ
    0.60
    Activations Density 0.073%

    No Known Activations