© 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. 26620
    Prev
    Next
    INDEX
    Explanations

    section headers and labels

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

    The neuron strongly activates on numeric tokens (sequences of digits) wherever they appear.

    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
     this
    -1.49
     what
    -1.41
     meticulously
    -1.38
     undeniably
    -1.35
     supremely
    -1.32
     epitom
    -1.30
     superbly
    -1.30
     massively
    -1.27
     subtly
    -1.25
     meticulous
    -1.22
    POSITIVE LOGITS
     astonishing
    1.42
    namely
    1.38
     marvelous
    1.34
     astounding
    1.34
     wondrous
    1.34
    indicated
    1.32
     AMAZING
    1.30
     horrid
    1.28
     😁
    1.26
     Dinas
    1.25
    Activations Density 0.000%

    No Known Activations