© 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. 34766
    Prev
    Next
    INDEX
    Explanations

    ordinals and ranks

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

    The neuron is keyed to numeric expressions (digits and related number‐count or statistic tokens) in the text.

    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
     nuevos
    -1.12
    همچنین
    -1.06
    new
    -1.04
    elyk
    -1.04
    INGRED
    -1.02
    mancy
    -1.01
    ztes
    -1.00
    そして
    -1.00
     effectiveness
    -0.99
    estris
    -0.98
    POSITIVE LOGITS
     Reihenfolge
    1.02
     Wochenende
    1.00
     ketiga
    1.00
     both
    0.90
     Auftrag
    0.90
     Vergangenheit
    0.90
     first
    0.88
    وير
    0.87
    ところに
    0.87
     constantemente
    0.86
    Activations Density 0.092%

    No Known Activations