© 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. 25779
    Prev
    Next
    INDEX
    Explanations

    numbers and dates

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

    The neuron activates on standalone numeric tokens (e.g. years, counts, or other numbers).

    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
     that
    -1.26
     five
    -1.21
     three
    -1.15
     fifteen
    -1.14
     eight
    -1.11
     italiano
    -1.11
     tunik
    -1.11
     fourteen
    -1.10
     thirteen
    -1.09
     twelve
    -1.08
    POSITIVE LOGITS
    >.
    1.17
     alcune
    1.16
     revamped
    1.13
     vastly
    1.13
     insanely
    1.09
     joyous
    1.09
     dessas
    1.09
     delightfully
    1.07
     applica
    1.07
     dando
    1.05
    Activations Density 0.031%

    No Known Activations