© 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. 22-GEMMASCOPE-RES-131K
    7. 130486
    Prev
    Next
    INDEX
    Explanations

    The main thing this neuron does is detect numeric expressions (numbers and digit‐based values) in the text.

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

    spending money on specific items

    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
     helado
    -1.19
     unangemessene
    -1.14
     MÉXICO
    -1.09
     boisson
    -1.08
    ремен
    -1.05
     新增
    -1.02
    Istorija
    -1.01
     löst
    -1.00
     Dumbledore
    -0.99
    kval
    -0.99
    POSITIVE LOGITS
     this
    1.67
     such
    1.44
     aforementioned
    1.18
     таком
    1.13
     above
    1.13
     these
    1.10
    这么
    1.09
     tersebut
    1.08
     solchen
    1.04
     aforesaid
    1.00
    Activations Density 0.049%

    No Known Activations