© 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. 39751
    Prev
    Next
    INDEX
    Explanations

    has been the

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

    The neuron activates on numeric tokens, i.e. occurrences of digits (dates, quantities, statistics) in the text.

    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
     then
    -1.88
     since
    -1.61
     subsequently
    -1.26
     that
    -1.16
     subsequent
    -1.16
     later
    -1.14
     podían
    -1.14
     henceforth
    -1.13
    guson
    -1.13
    sequently
    -1.13
    POSITIVE LOGITS
     S
    1.20
     
    1.16
    ne
    1.16
    is
    1.15
    S
    1.13
    着一个
    1.12
     "
    1.07
    )।
    1.04
    了一会儿
    1.04
     D
    1.02
    Activations Density 0.073%

    No Known Activations