© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 1263
    Prev
    Next
    INDEX
    Explanations

    ordinal and numerical identifiers

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

    The neuron primarily activates on numeric tokens (e.g. numbers, indexes, and counts) 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_34/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
     также
    -1.39
    を行い
    -1.36
    の方も
    -1.29
    の方に
    -1.27
     também
    -1.25
    割と
    -1.24
    すっ
    -1.23
    を作って
    -1.23
    すご
    -1.22
    来週
    -1.22
    POSITIVE LOGITS
     is
    2.06
     was
    1.51
     just
    1.48
     has
    1.31
    ,
    1.25
    は
    1.25
     an
    1.23
    が
    1.14
     theirs
    1.14
     by
    1.14
    Activations Density 0.107%

    No Known Activations