© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 68742
    Prev
    Next
    INDEX
    Explanations

    available, recognized, produced, offered

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

    The neuron activates on numeric expressions—counts, measurements, years, and other 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_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
     where
    -1.48
     by
    -1.41
     two
    -1.29
     without
    -1.29
     some
    -1.27
     it
    -1.23
     another
    -1.22
     was
    -1.21
     several
    -1.18
     if
    -1.17
    POSITIVE LOGITS
     현재
    1.22
     dzisiaj
    1.18
     geene
    1.18
     différents
    1.15
     jelasnya
    1.10
     които
    1.09
     plafon
    1.09
     différentes
    1.09
     sonhos
    1.08
    vial
    1.05
    Activations Density 0.117%

    No Known Activations