© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 128528
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on occurrences of concrete statistical or numerical data (counts, percentages, measurements) in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    United States and worldwide

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     in
    -1.63
     southeast
    -1.35
     northeastern
    -1.32
     wensen
    -1.30
     across
    -1.30
     north
    -1.28
     south
    -1.23
     northwest
    -1.19
     west
    -1.17
     northeast
    -1.17
    POSITIVE LOGITS
    で
    1.30
    を
    1.13
    </th>
    1.09
    「
    1.09
    »
    1.08
    r
    1.05
     »
    1.02
    が
    1.01
    これ
    0.99
     •
    0.98
    Activations Density 0.171%

    No Known Activations