© 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. 128410
    Prev
    Next
    INDEX
    Explanations

    The neuron activates on numeric tokens (i.e. sequences of digits).

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

    end of sentence punctuation and conjunctions

    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
     cetera
    -1.05
     ayrıca
    -1.03
    应对
    -1.02
    两种
    -1.01
     grec
    -0.97
    πί
    -0.95
    sowie
    -0.95
    ølge
    -0.94
     également
    -0.94
    rii
    -0.93
    POSITIVE LOGITS
     now
    1.62
     but
    1.52
     shouldn
    1.17
     подобрать
    1.09
     this
    1.09
     isn
    1.07
     these
    1.06
     too
    1.05
     today
    1.05
    だけど
    1.04
    Activations Density 0.007%

    No Known Activations