© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 70490
    Prev
    Next
    INDEX
    Explanations

    numbers in lists

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

    The neuron fires on standalone numeric tokens (digits, including signed or decimal 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
    -1.37
     when
    -1.21
     at
    -1.09
    обы
    -1.07
     usually
    -1.04
     Usually
    -1.04
     this
    -1.03
     When
    -1.02
     as
    -1.01
     or
    -1.00
    POSITIVE LOGITS
     alcune
    1.27
     molti
    1.13
     certaines
    1.13
    色々と
    1.10
     plusieurs
    1.10
     molte
    1.09
    色々な
    1.09
    ほんとに
    1.08
     abends
    1.07
     komplet
    1.02
    Activations Density 0.038%

    No Known Activations