© 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. 10960
    Prev
    Next
    INDEX
    Explanations

    the followed by noun

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

    The neuron is triggered by numerical expressions (digits, figures, and other number‐like tokens) 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
     their
    -1.25
     diferenças
    -1.24
     беже
    -1.22
     соответственно
    -1.20
    gnąć
    -1.19
     respetu
    -1.18
     presentará
    -1.17
     rád
    -1.15
     descubre
    -1.14
    ところに
    -1.13
    POSITIVE LOGITS
     this
    2.11
     it
    1.88
     denna
    1.27
    pography
    1.23
     lenge
    1.21
     corpi
    1.21
     augusti
    1.20
     event
    1.20
     rey
    1.18
     robuste
    1.17
    Activations Density 0.107%

    No Known Activations