© 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. 34-GEMMASCOPE-RES-131K
    7. 33119
    Prev
    Next
    INDEX
    Explanations

    android code

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

    The neuron fires on numeric tokens (e.g. numbers in dates, tables, measurements, etc.).

    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
     appartement
    -1.36
     kaffe
    -1.29
     tappa
    -1.18
     mense
    -1.16
     produt
    -1.14
     Père
    -1.13
     trev
    -1.12
     uhd
    -1.12
     Stampa
    -1.10
     tuh
    -1.10
    POSITIVE LOGITS
     daje
    1.41
     всички
    1.38
     pokaz
    1.33
     mencapai
    1.28
     всі
    1.24
     &
    1.23
     žena
    1.23
     различни
    1.22
     jednej
    1.21
     liczba
    1.21
    Activations Density 0.014%

    No Known Activations