© 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. 16263
    Prev
    Next
    INDEX
    Explanations

    numbers and symbols

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

    The neuron strongly activates on multi‐digit numeric tokens (i.e. numbers with two or more digits).

    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
     first
    -1.83
     those
    -1.74
     all
    -1.69
     other
    -1.67
     after
    -1.66
     primarily
    -1.63
     reduce
    -1.63
     for
    -1.62
     what
    -1.59
     prevent
    -1.58
    POSITIVE LOGITS
     trám
    1.74
     Dinas
    1.48
     médicaments
    1.45
     sooo
    1.43
     花纹
    1.41
    髫
    1.41
     soooo
    1.41
     SHOCK
    1.40
    俨
    1.37
     apparaissent
    1.35
    Activations Density 0.001%

    No Known Activations