© 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. 130616
    Prev
    Next
    INDEX
    Explanations

    The neuron detects numeric tokens (e.g. integers or decimals) in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    degree of frequency and likelihood

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     libéral
    -1.34
    缡
    -1.29
     eſſ
    -1.26
     masaj
    -1.21
     fré
    -1.20
     Chambres
    -1.20
     officier
    -1.20
    mları
    -1.19
     église
    -1.19
     extrait
    -1.18
    POSITIVE LOGITS
    往往
    1.47
     sometimes
    1.36
     it
    1.29
    常常
    1.27
     their
    1.26
    有时
    1.20
     at
    1.17
     as
    1.15
     often
    1.14
     and
    1.13
    Activations Density 0.023%

    No Known Activations