© 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. 108867
    Prev
    Next
    INDEX
    Explanations

    to a

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

    The neuron detects numeric tokens—any sequence of digits 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
     различных
    -1.36
     некоторых
    -1.26
     отдельных
    -1.23
     leerlingen
    -1.23
     wielu
    -1.20
     различни
    -1.20
     разных
    -1.20
     każdego
    -1.19
     geloof
    -1.18
     hervorragend
    -1.16
    POSITIVE LOGITS
     a
    4.06
     such
    3.33
     an
    2.66
     столь
    2.58
     something
    2.52
     what
    2.48
     такой
    2.31
     this
    2.20
     چنین
    2.20
    such
    2.17
    Activations Density 0.121%

    No Known Activations