© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 38628
    Prev
    Next
    INDEX
    Explanations

    numbers or quantities

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

    This neuron specifically activates on the spelled-out cardinal number “Two.”

    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
    yship
    -1.55
    voer
    -1.41
     diciembre
    -1.36
    вної
    -1.31
     mendes
    -1.29
    backers
    -1.27
    ariats
    -1.24
     memperbaiki
    -1.23
    gings
    -1.22
     their
    -1.20
    POSITIVE LOGITS
     of
    2.17
     have
    1.44
    はこんな感じ
    1.35
     thing
    1.20
     questions
    1.19
    Things
    1.17
     traseiro
    1.17
     years
    1.17
    就直接
    1.15
    ’
    1.15
    Activations Density 0.056%

    No Known Activations